Using Graphs to Perform Effective Sensor-Based Human Activity Recognition in Smart Homes.

There has been a resurgence of applications focused on human activity recognition (HAR) in smart homes, especially in the field of ambient intelligence and assisted-living technologies. However, such applications present numerous significant challenges to any automated analysis system operating in the real world, such as variability, sparsity, and noise in sensor measurements. Although state-of-the-art HAR systems have made considerable strides in addressing some of these challenges, they suffer from a practical limitation: they require successful pre-segmentation of continuous sensor data streams prior to automated recognition, i.

Improving biosensor accuracy and speed using dynamic signal change and theory-guided deep learning.

False results and time delay are longstanding challenges in biosensing. While classification models and deep learning may provide new opportunities for improving biosensor performance, such as measurement confidence and speed, it remains a challenge to ensure that predictions are explainable and consistent with domain knowledge. Here, we show that consistency of deep learning classification model predictions with domain knowledge in biosensing can be achieved by cost function supervision and enables rapid and accurate biosensing using the biosensor dynamic response.

Reduction of Biosensor False Responses and Time Delay Using Dynamic Response and Theory-Guided Machine Learning.

Here, we provide a new methodology for reducing false results and time delay of biosensors, which are barriers to industrial, healthcare, military, and consumer applications. We show that integrating machine learning with domain knowledge in biosensing can complement and improve the biosensor accuracy and speed relative to the performance achieved by traditional regression analysis of a standard curve based on the biosensor steady-state response. The methodology was validated by rapid and accurate quantification of microRNA across the nanomolar to femtomolar range using the dynamic response of cantilever biosensors.

A TTFS-based energy and utilization efficient neuromorphic CNN accelerator.

Spiking neural networks (SNNs), which are a form of neuromorphic, brain-inspired AI, have the potential to be a power-efficient alternative to artificial neural networks (ANNs). Spikes that occur in SNN systems, also known as activations, tend to be extremely sparse, and low in number. This minimizes the number of data accesses typically needed for processing.

A novel zernike application to differentiate between three-dimensional corneal thickness of normal corneas and corneas with keratoconus.

Purpose: To evaluate a novel Zernike algorithm to differentiate 3-dimensional (3-D) corneal thickness distribution of corneas with keratoconus (KC) from normal corneas.

Design: A retrospective development and evaluation of a diagnostic approach.

Methods: Corneal tomography with Scheimpflug imaging was performed in normal (43 eyes) and KC (85 eyes) corneas.

Understanding the Correlation between Tomographic and Biomechanical Severity of Keratoconic Corneas.

Purpose. To evaluate correlation between tomographic gradation of keratoconus (KC) and its corresponding air-puff induced biomechanical response. Methods.

Attenuation of lysyl oxidase and collagen gene expression in keratoconus patient corneal epithelium corresponds to disease severity.

Purpose: Keratoconus (KC) is characterized by progressive vision loss due to corneal thinning and structural abnormalities. It is hypothesized that KC is caused by deregulated collagen levels and collagen fibril-maturating enzyme lysyl oxidase (LOX). Further, it is currently not understood whether the gene expression deregulated by the corneal epithelium influences KC pathogenesis.

Salvage whole-abdominal radiation therapy after second-look laparotomy or secondary debulking surgery in patients with ovarian cancer.

Objectives: Our aim was to determine the outcomes associated with use of whole-abdominal radiation therapy (WART) in women with ovarian cancer, to identify predictors of response, and to assess associated toxicity.

Methods: From 1981 through 2000, 171 women received WART at our institution after ovarian cancer surgery. Relevant clinical information was extracted through retrospective chart review.

Overexpression of p34cdc2 protein kinase in epithelial ovarian carcinoma.

Objective: To investigate the role of expression of p34cdc2 protein kinase in normal, benign, and malignant ovarian epithelium.

Material And Methods: Tissue sections from 24 patients with epithelial ovarian carcinoma (EOC) along with 6 normal ovarian specimens and 12 benign cystadenomas were incubated with mouse IgG monoclonal antibody to human p34cdc2 protein kinase, followed by detection with use of a standard peroxidase-labeled streptavidin-biotin technique. Immunohistochemical staining was graded and compared.

Expression of nm23/nucleoside diphosphate kinase-A protein in endometrial carcinoma.

A metastatic tumor suppressor role for the nm23 gene product in breast carcinoma has been proposed. The biologic significance of nm23/NDP kinase-A (NDPK-A) expression in endometrial carcinoma remains undetermined. We sought to (1) characterize the pattern and intensity of nm23 protein expression in endometrial carcinoma and (2) assess the relationship between intensity/pattern of nm23 protein immunostaining and treatment response assessed by progression-free survival and survival to death.

Spontaneous intrauterine linear skull fracture: a rare complication of spontaneous vaginal delivery.

Background: Fetal skull fracture has been reported in conjunction with difficult delivery or extrinsic trauma.

Case: We report a case of linear, undisplaced, nondepressed skull fracture occurring in a 3540-g male infant born at 37 weeks and 4 days' gestation. Linear skull fracture occurred despite an uncomplicated spontaneous vaginal delivery in the absence of extrinsic trauma or cephalopelvic disproportion.

Elevated nm23 protein expression is correlated with diminished progression-free survival in patients with epithelial ovarian carcinoma.

Objectives: The role of the candidate metastasis-suppressor gene nm23-H1 first characterized in breast cancer remains controversial, with both metastasis suppression and disease progression being linked to elevated nm23-H1 gene expression in different human tumor types. We sought to characterize (1) the pattern and intensity of nm23-H1/nucleoside diphosphate (NDP) kinase expression in human epithelial ovarian carcinoma (EOC) and (2) the relationship between nm23-H1/NDP kinase expression and tumor extent at diagnosis (FIGO stage) and response to treatment as defined by progression-free survival and actuarial survival.

Methods: Twenty-four patients with EOC aged 61.

Disseminated cervical adenoma malignum and bilateral ovarian sex cord tumors with annular tubules associated with Peutz-Jeghers syndrome.

Adenoma malignum is a highly differentiated mucinous adenocarcinoma of the cervix with a deceptively innocent histologic appearance but a highly aggressive behavior. We describe a patient who had adenoma malignum associated with Peutz-Jeghers syndrome (PJS) and bilateral ovarian sex cord tumor with annular tubules (SCTAT). The relatively frequent occurrence of cervical adenoma malignum in women with PJS warrants close surveillance by gynecologists for early detection and treatment of this cancer.