Neural Network Layer Algebra: A Framework to Measure Capacity and Compression in Deep Learning.

We present a new framework to measure the intrinsic properties of (deep) neural networks. While we focus on convolutional networks, our framework can be extrapolated to any network architecture. In particular, we evaluate two network properties, namely, capacity, which is related to expressivity, and compression, which is related to learnability. Both these properties depend only on the network structure and are independent of the network parameters. To this end, we propose two metrics: the first one, called layer complexity, captures the architectural complexity of any network layer; and, the second one, called layer intrinsic power, encodes how data are compressed along the network. The metrics are based on the concept of layer algebra, which is also introduced in this article. This concept is based on the idea that the global properties depend on the network topology, and the leaf nodes of any neural network can be approximated using local transfer functions, thereby allowing a simple computation of the global metrics. We show that our global complexity metric can be calculated and represented more conveniently than the widely used Vapnik-Chervonenkis (VC) dimension. We also compare the properties of various state-of-the-art architectures using our metrics and use the properties to analyze their accuracy on benchmark image classification datasets.

Development of multifunctional food packaging films based on waste Garlic peel extract and Chitosan.

A sustainable multifunctional food packaging composite film containing waste garlic peel extract (GPE) and Chitosan (CH) was prepared. This film exhibited antimicrobial potential towards Staphylococcus aureus and Klebsiella pneumoniae. GPE/CH films' morphological, physical, and functional properties were compared to those of CH film. Fourier transform infrared showed the interactions through hydrogen bonding between CH and GPE in the blends that improved the polymers' compatibility. Furthermore, X-ray diffraction analysis validated the compatibility between GPE and CH. GPE/CH films exhibited higher thickness and moisture content than the CH film. Remarkably, GPE/CH films showed lower water vapor barrier properties and higher ultra-violet protection and mechanical strength than CH film. Compact surfaces of the GPE infused CH films were unveiled through Scanning electron microscopy. GPE/CH film showed improved thermal stability after the addition of GPE. MTT method's cytotoxicity study manifested that the GPE/CH films are antioxidant and non-cytotoxic, implicating their biocompatibility and non-toxicity. The results suggest that GPE/CH films can find widespread commercial applications like food packaging materials, replacing the commonly used petrochemical plastics.

Key policy and programmatic factors to improve influenza vaccination rates based on the experience from four high-performing countries.

BACKGROUND: Many countries consistently fail to achieve the target influenza vaccine coverage rate (VCR) of 75% for populations at risk of complications, recommended by the World Health Organization and European Council. We aimed to identify factors for achieving a high VCR in the scope of four benchmark countries with high influenza VCRs: Australia, Canada, UK and USA. METHODS: Publicly available evidence was first reviewed at a global level and then for each of the four countries. Semi-structured interviews were then conducted with stakeholders meeting predefined criteria. Descriptive cluster analyses were performed to identify key factors and pillars for establishing and maintaining high VCRs. RESULTS: No single factor led to a high VCR, and each benchmark country used a different combination of tailored approaches to achieve a high vaccine coverage. In each country, specific triggers were important to stimulate changes that led to improved vaccine coverage. A total of 42 key factors for a successful influenza vaccination programme were identified and clustered into five pillars: (1) Health Authority accountability and strengths of the influenza programme, (2) facilitated access to vaccination, (3) healthcare professional accountability and engagement, (4) awareness of the burden and severity of disease and (5) belief in influenza vaccination benefit. Each benchmark country has implemented multiple factors from each pillar. CONCLUSION: A wide range of factors were identified from an evaluation of four high-performing benchmark countries, classified into five pillars, thus providing a basis for countries with lower VCRs to tailor their own particular solutions to improve their influenza VCR.

Identifying characteristics that impact motor carrier safety using Bayesian networks.

PROBLEM STATEMENT: In the U.S., a safety rating is assigned to each motor carrier based on data obtained from the Motor Carrier Management Information System (MCMIS) and an on-site investigation. While researchers have identified variables associated with the safety ratings, the specific direction of the relationships are not necessarily clear. OBJECTIVE: The objective of this study is to identify those relationships involved in the safety ratings of interstate motor carriers, the largest users of the U.S. transportation network. METHOD: Bayesian networks are used to learn these relationships from data obtained from MCMIS for a 6-year period (2007-2012). RESULTS: Our study shows that safety rating assignment is a complex process with only a subset of the variables having statistically significant relationship with safety rating. They include driver out-of-service violations, weight violations, traffic violations, fleet size, total employed drivers, and passenger & general carrier indicators. APPLICATION: The findings have both immediate implications and long term benefits. The immediate implications relate to better identification of unsafe motor carriers, and the long term benefits pertain to policies and crash countermeasures that can enhance carrier safety.

Predicting interstate motor carrier crash rate level using classification models.

Ensuring safe operations of large commercial vehicles (motor carriers) remains an important challenge, particularly in the United States. While the federal regulatory agency has instituted a compliance review-based rating method to encourage carriers to improve their safety levels, concerns have been expressed regarding the effectiveness of the current ratings. In this paper, we consider a crash rate level (high, medium, and low) rather than a compliance review-based rating (satisfactory, conditional satisfactory, and unsatisfactory). We demonstrate an automated way of predicting the crash rate levels for each carrier using three different classification models (Artificial Neural Network, Classification and Regression Tree (CART), and Support Vector Machine) and three separate variable selection methods (Empirical Evidence, Multiple Factor Analysis, Garson's algorithm). The predicted crash rate levels (high, low) are compared to the assigned levels based on the current safety rating method. The results indicate the feasibility of crash rate level as an effective measure of carrier safety, with CART having the best performance.

An analysis of the most common types of hand injury mistakes and their cost in the acute setting.

This study aimed to explore the most common hand injury errors occurring in Emergency Departments in England. A Freedom of Information request was made to the NHS Litigation Authority for claims data related to hand injuries in English Emergency Departments from 2004 to 2014. All successful hand injury claims against an individual DGH ED were also analysed. Two hundred and eighteen successful claims were made, costing a total of £6,273,688.22. Diagnosis error was the most common successful claim (97). Four successful claims were brought against the Emergency Department. Causes of error included the use of inappropriate views and failure to correlate imaging with clinical findings. Hand injury diagnostic error has been the most common cause of successful litigious claims against Emergency Departments over the past 10 years. This paper demonstrates that fracture recognition and clinical diagnosis of hand injuries are key areas to target to reduce error rates.

An Associative Memory Model for Integration of Fragmented Research Data and Identification of Treatment Correlations in Breast Cancer Care.

A major challenge in advancing scientific discoveries using data-driven clinical research is the fragmentation of relevant data among multiple information systems. This fragmentation requires significant data-engineering work before correlations can be found among data attributes in multiple systems. In this paper, we focus on integrating information on breast cancer care, and present a novel computational approach to identify correlations between administered drugs captured in an electronic medical records and biological factors obtained from a tumor registry through rapid data aggregation and analysis. We use an associative memory (AM) model to encode all existing associations among the data attributes from both systems in a high-dimensional vector space. The AM model stores highly associated data items in neighboring memory locations to enable efficient querying operations. The results of applying AM to a set of integrated data on tumor markers and drug administrations discovered anomalies between clinical recommendations and derived associations.

Comparing the performance of expert user heuristics and an integer linear program in aircraft carrier deck operations.

Planning operations across a number of domains can be considered as resource allocation problems with timing constraints. An unexplored instance of such a problem domain is the aircraft carrier flight deck, where, in current operations, replanning is done without the aid of any computerized decision support. Rather, veteran operators employ a set of experience-based heuristics to quickly generate new operating schedules. These expert user heuristics are neither codified nor evaluated by the United States Navy; they have grown solely from the convergent experiences of supervisory staff. As unmanned aerial vehicles (UAVs) are introduced in the aircraft carrier domain, these heuristics may require alterations due to differing capabilities. The inclusion of UAVs also allows for new opportunities for on-line planning and control, providing an alternative to the current heuristic-based replanning methodology. To investigate these issues formally, we have developed a decision support system for flight deck operations that utilizes a conventional integer linear program-based planning algorithm. In this system, a human operator sets both the goals and constraints for the algorithm, which then returns a proposed schedule for operator approval. As a part of validating this system, the performance of this collaborative human-automation planner was compared with that of the expert user heuristics over a set of test scenarios. The resulting analysis shows that human heuristics often outperform the plans produced by an optimization algorithm, but are also often more conservative.

Measurement and implications of postural changes in blood pressure.

Postural changes in blood pressure are a commonly elicited vital sign. It is important that the measurements are reproducible in order to be clinically meaningful. This article makes recommendations about how and what to document as part of the technique of recording, on the basis of the literature.

Survey on indirect optical manipulation of cells, nucleic acids, and motor proteins.

Optical tweezers have emerged as a promising technique for manipulating biological objects. Instead of direct laser exposure, more often than not, optically-trapped beads are attached to the ends or boundaries of the objects for translation, rotation, and stretching. This is referred to as indirect optical manipulation. In this paper, we utilize the concept of robotic gripping to explain the different experimental setups which are commonly used for indirect manipulation of cells, nucleic acids, and motor proteins. We also give an overview of the kind of biological insights provided by this technique. We conclude by highlighting the trends across the experimental studies, and discuss challenges and promising directions in this domain of active current research.

The prevalence of polypharmacy in elderly attenders to an emergency department - a problem with a need for an effective solution.

We studied the prevalence of polypharmacy in attenders aged 75 years and over to an emergency department (ED) in North London over a period of 1 month. We identified 467 patients in this age group. Analysis of medications being prescribed revealed at least 82 patients on medication with the potential for adverse interaction. There is a need for ED-initiated strategies to identify interactions and for pathways to allow for medication review.

A potentially missed cervical (C2) spine fracture.

The authors present a case report of a potentially missed C2 fracture whose signs and symptoms did not warrant radiograph imaging according to both the National Emergency X-Radiography Utilization Study and Canadian C-spine Rules. The patient had a significant injury while rear-ending a stationary vehicle at 20 mph, and the correct diagnosis was only made based on approaching him with a high index of suspicion. He was successfully treated in a halo collar and made an excellent recovery.

The role of prophylactic anticonvulsants in moderate to severe head injury.

BACKGROUND: Post-traumatic seizures cause secondary brain injury, contributing to morbidity and mortality after traumatic brain injury. Seizure activity may be undetectable if the patient is paralysed and ventilated. AIMS: The effect of prophylactic anticonvulsant therapy on the prevention of seizures after moderate to severe traumatic brain injury was studied. METHODS: A structured systematic literature review was performed. RESULTS: There may be a place for prophylactic anticonvulsants in the prophylaxis of early post-traumatic seizures. CONCLUSION: Further randomised controlled trials are needed to firmly establish the benefits of prophylactic anticonvulsants.

Look but do not fix: the pioneers of interventional cardiovascular radiology.

The extension of endovascular radiological procedures to a one-stop combined investigation and treatment of cardiovascular disease has revolutionized clinical practice. The giants in this respect are Charles Dotter, working from Portland, OR; Mason Sones from the Cleveland Clinic; and Andreas Gruentzig from Zurich and latterly Atlanta, GA. Serendipity and lateral thinking were pivotal in developing procedures that are now routine.

Acute dysphagia: an unusual treatable cause.

Bariatric surgery is a rapidly expanding surgical sub-speciality, with a large proportion of the relevant surgical procedures being performed in the private sector. Acute complications of newer surgical procedures can lead to emergency department presentation, with which the staff may be unfamiliar. A 34-year-old woman was seen in the emergency department with acute total dysphagia following laparoscopic adjustable gastric banding, which was treated successfully by a simple bedside procedure.

Assessment and management of posttraumatic haemarthrosis of the knee.

Traumatic haemarthrosis of the knee poses significant diagnostic difficulty in the acute phase. Orthopaedic follow up is essential. An update of current recommended practice is provided, and the pros and cons of arthroscopy and magnetic resonance imaging are discussed.

C Walton Lillehei (1918-99): the versatile pioneer of open-heart surgery.

Walton Lillehei can be truly regarded as the 'Father of Open-Heart Surgery'. His career demonstrates the virtues of tenacity and the ability to overcome adversity and opposition in the taking forward of significant innovation.

Synthesis and characterization of tricalcium phosphate with Zn and Mg based dopants.

The purpose of this study is to prepare tricalcium phosphate (TCP) ceramic by dual dopants of magnesium (Mg) and zinc (Zn), and investigate the influence of dopants on the physical, mechanical and biological properties of TCP. TCP were synthesized with 1 wt% Mg, 0.3 wt% Zn and dual dopants using the precipitation process. Phase composition and microstructures were characterized. Mechanical properties and dissolution behavior in vitro were investigated. Human osteoblast cell culture was used to determine the influence of dopants on cell-materials interactions. XRD analysis indicated that Mg delayed phase transformation from beta to alpha-TCP and pure beta-TCP phase was obtained for Mg-doped TCP after sintered at 1250 degrees C. Addition of Mg improved densification behavior of TCP. Compression strength also increased from 24.0 MPa to 77.2 MPa after doping with Mg and Zn. Furthermore, Mg additive reduced the solubility of TCP in vitro. Osteoblast culture studies indicated that the presence of Mg stabilized the cell-material interface and thus improved cell attachment and growth. Zn-doped TCP exhibited good bioactivity, which enhanced cell differentiation and alkaline phosphatase (ALP) expression. The highest cell proliferation and ALP expression were found on dual Mg and Zn doped TCP. The results indicate that Mg and Zn dopants play a significant role towards improving mechanical properties and cell-materials interactions of TCP. This work also demonstrates the potential for dual Mg and Zn doped TCP to be used in orthopedics and dentistry, which displays high mechanical strength, low resorption and improved cell-material interaction.