scholarly journals Multicamera 3D Viewpoint Adjustment for Robotic Surgery via Deep Reinforcement Learning

2021 ◽  
pp. 2140003
Author(s):  
Yun-Hsuan Su ◽  
Kevin Huang ◽  
Blake Hannaford
Keyword(s):  
Reinforcement Learning ◽  
Haptic Feedback ◽  
Research Effort ◽  
Spatial Awareness ◽  
Ongoing Research ◽  
Incision Size ◽  
Patient Pain ◽  
Positioning Method ◽  
Lower Infection ◽  
Improved Performance

While robot-assisted minimally invasive surgery (RMIS) procedures afford a variety of benefits over open surgery and manual laparoscopic operations (including increased tool dexterity, reduced patient pain, incision size, trauma and recovery time, and lower infection rates [1], lack of spatial awareness remains an issue. Typical laparoscopic imaging can lack sufficient depth cues and haptic feedback, if provided, rarely reflects realistic tissue–tool interactions. This work is part of a larger ongoing research effort to reconstruct 3D surfaces using multiple viewpoints in RMIS to increase visual perception. The manual placement and adjustment of multicamera systems in RMIS are nonideal and prone to error [2], and other autonomous approaches focus on tool tracking and do not consider reconstruction of the surgical scene [3-5]. The group’s previous work investigated a novel, context-aware autonomous camera positioning method [6], which incorporated both tool location and scene coverage for multiple camera viewpoint adjustments. In this paper, the authors expand upon this prior work by implementing a streamlined deep reinforcement learning approach between optimal viewpoints calculated using the prior method [6] which encourages discovery of otherwise unobserved and additional camera viewpoints. Combining the framework and robustness of the previous work with the efficiency and additional viewpoints of the augmentations presented here results in improved performance and scene coverage promising towards real-time implementation.

scholarly journals An REU Experience With Micro Assembly Workcell Research

2010 ◽  
Vol 1 (1) ◽  
pp. 35-42 ◽  
Author(s):  
William Stapleton ◽  
Bahram Asiabanpour ◽  
Jesus Jimenez ◽  
Dugan Um
Keyword(s):  
Undergraduate Students ◽  
Haptic Feedback ◽  
Vision System ◽  
Dimensional Space ◽  
Research Effort ◽  
Three Dimensional ◽  
Prototype System ◽  
Ongoing Research ◽  
Corpus Christi ◽  
Visual Sensing

Under an NSF REU center grant REU-0755355 entitled “Micro/Nano Assembly Workcell Via Micro Visual Sensing and Haptic Feedback”, Texas A&M University – Corpus Christi and Texas State University – San Marcos collaboratively hosted two groups of 10 students from different backgrounds for 10 weeks each in Summer 2008 and 2009 respectively.  The research effort involved is part of an ongoing research program developing novel methods for making automated micromanipulation systems.  The twenty students and two teachers were divided into four teams developing interrelated aspects of the project.  The first team developed the micro-scale parts, such as gears, for assembly.  This required the team to develop techniques for etch and release of three dimensional parts from a silicon substrate.  The second team developed the microscopic vision system used for locating and identifying parts on a silicon wafer.  The vision system is used to determine the position on the wafer of the parts, their diameter (one of several standard parts), and, utilizing a novel technique developed by the team, the thickness of the parts.  The third team developed a robotic platform able to locate any portion of a wafer for manipulation within a three-dimensional space with 10μm accuracy.  This mechanism is used to first bring any desired portion of the wafer to the vision system for analysis and also to bring a manipulator to “pick and place” parts using the vision system for feedback.  The fourth group developed the micro-manipulator in the form of a “gripper” powered by electro-active polymer.  This gripper was capable of accurately and repeatably gripping, lifting, moving, placing, and releasing parts at any point within the workspace.  Collectively, the REU project successfully produced a prototype system advancing the state-of-art for an important are of micro-manufacturing while offering a stimulating experience for undergraduate students.  Assessment of the student experience showed an increase in the likelihood for these students to pursue engineering careers and to encourage their peers to consider STEM careers.

scholarly journals Selective network discovery via deep reinforcement learning on embedded spaces

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Peter Morales ◽  
Rajmonda Sulo Caceres ◽  
Tina Eliassi-Rad
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Sequential Decision ◽  
Network Discovery ◽  
Learning Tasks ◽  
Partially Observed ◽  
Decision Making Problem ◽  
Resource Collection ◽  
Improved Performance ◽  
Discovery Algorithms

AbstractComplex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the network can be costly and nontrivial. As a result, network discovery algorithms optimized for specific downstream learning tasks given resource collection constraints are of great interest. In this paper, we formulate the task-specific network discovery problem as a sequential decision-making problem. Our downstream task is selective harvesting, the optimal collection of vertices with a particular attribute. We propose a framework, called network actor critic (NAC), which learns a policy and notion of future reward in an offline setting via a deep reinforcement learning algorithm. The NAC paradigm utilizes a task-specific network embedding to reduce the state space complexity. A detailed comparative analysis of popular network embeddings is presented with respect to their role in supporting offline planning. Furthermore, a quantitative study is presented on various synthetic and real benchmarks using NAC and several baselines. We show that offline models of reward and network discovery policies lead to significantly improved performance when compared to competitive online discovery algorithms. Finally, we outline learning regimes where planning is critical in addressing sparse and changing reward signals.

scholarly journals Novel Treatments and Technologies Applied to the Cure of Neuroblastoma

Children ◽  
2021 ◽  
Vol 8 (6) ◽  
pp. 482
Author(s):  
Irene Paraboschi ◽  
Laura Privitera ◽  
Gabriela Kramer-Marek ◽  
John Anderson ◽  
Stefano Giuliani
Keyword(s):  
Research Effort ◽  
Treatment Strategies ◽  
Adverse Outcomes ◽  
Treatment Protocols ◽  
Ongoing Research ◽  
Hematopoietic Stem ◽  
Novel Treatments ◽  
Therapeutic Modalities ◽  
High Risk Disease ◽  
Novel Treatment Strategies

Neuroblastoma (NB) is the most common extracranial solid tumour in childhood, accounting for approximately 15% of all cancer-related deaths in the paediatric population1. It is characterised by heterogeneous clinical behaviour in neonates and often adverse outcomes in toddlers. The overall survival of children with high-risk disease is around 40–50% despite the aggressive treatment protocols consisting of intensive chemotherapy, surgery, radiation therapy and hematopoietic stem cell transplantation2,3. There is an ongoing research effort to increase NB’s cellular and molecular biology knowledge to translate essential findings into novel treatment strategies. This review aims to address new therapeutic modalities emerging from preclinical studies offering a unique translational opportunity for NB treatment.

A Numerical Investigation of Aeroacoustic Fan Blade Flutter

2003 ◽  
Author(s):  
X. Wu ◽  
M. Vahdati ◽  
A. I. Sayma ◽  
M. Imregun
Keyword(s):  
Research Effort ◽  
Pressure Rise ◽  
Acoustic Properties ◽  
Pressure Amplitude ◽  
Ongoing Research ◽  
Blade Flutter ◽  
Fan Blade ◽  
Underlying Mechanisms ◽  
Flutter Margin

This paper reports the results of an ongoing research effort to explain the underlying mechanisms for aeroacoustic fan blade flutter. Using a 3D integrated aeroelasticity method and a single passage blade model that included a representation of the intake duct, the pressure rise vs. mass flow characteristic of a fan assembly was obtained for the 60%–80% speed range. A novel feature was the use of a downstream variable-area nozzle, an approach that allowed the determination of the stall boundary with good accuracy. The flutter stability was predicted for the 2 nodal diameter assembly mode arising from the first blade flap mode. The flutter margin at 64% speed was predicted to drop sharply and the instability was found to be independent of stall effects. On the other hand, the flutter instability at 74% speed was found to be driven by flow separation. Further post-processing of the results at 64% speed indicated significant unsteady pressure amplitude build-up inside the intake at the flutter condition, thus highlighting the link between the acoustic properties of the intake duct and fan blade flutter.

Development of High Temperature Liquid Metal Heat Transfer Fluids for CSP Applications

2014 ◽  
Author(s):  
Gopinath R. Warrier ◽  
Y. Sungtaek Ju ◽  
Jan Schroers ◽  
Mark Asta ◽  
Peter Hosemann
Keyword(s):  
Heat Transfer ◽  
High Temperature ◽  
Liquid Metal ◽  
Liquid Metals ◽  
Research Effort ◽  
Structural Materials ◽  
Forced Flow ◽  
Oxygen Control ◽  
Ongoing Research ◽  
Heat Transfer Fluids

In response to the DOE Sunshot Initiative to develop low-cost, high efficiency CSP systems, UCLA is leading a multi-university research effort to develop new high temperature heat transfer fluids capable of stable operation at 800°C and above. Due to their operating temperature range, desirable heat transfer properties and very low vapor pressure, liquid metals were chosen as the heat transfer fluid. An overview of the ongoing research effort is presented. Development of new liquid metal coolants begins with identification of suitable candidate metals and their alloys. Initial selection of candidate metals was based on such parameters as melting temperature, cost, toxicity, stability/reactivity Combinatorial sputtering of the down selected candidate metals is used to fabricate large compositional spaces (∼ 800), which are then characterized using high-throughput techniques (e.g., X-ray diffraction). Massively parallel optical methods are used to determine melting temperatures. Thermochemical modeling is also performed concurrently to compliment the experimental efforts and identify candidate multicomponent alloy systems that best match the targeted properties. The modeling effort makes use of available thermodynamic databases, the computational thermodynamic CALPHAD framework and molecular-dynamics simulations of molten alloys. Refinement of available thermodynamics models are performed by comparison with available experimental data. Characterizing corrosion in structural materials such as steels, when using liquid metals, and strategies to mitigate them are an integral part of this study. The corrosion mitigation strategy we have adopted is based on the formation of stable oxide layers on the structural metal surface which prevents further corrosion. As such oxygen control is crucial in such liquid metal systems. Liquid metal enhanced creep and embrittlement in commonly used structural materials are also being investigated. Experiments with oxygen control are ongoing to evaluate what structural materials can be used with liquid metals. Characterization of the heat transfer during forced flow is another key component of the study. Both experiments and modeling efforts have been initiated. Key results from experiments and modeling performed over the last year are highlighted and discussed.

Technological advances in high-efficiency particulate collection

1997 ◽  
Vol 211 (1) ◽  
pp. 53-65 ◽  
Author(s):  
K R Parker
Keyword(s):  
High Efficiency ◽  
Electrostatic Precipitator ◽  
Cost Effective ◽  
Vapour Phase ◽  
Air Toxics ◽  
Bag Filter ◽  
Element Analysis ◽  
Ongoing Research ◽  
Technological Advances ◽  
Improved Performance

Particulate control equipment for the larger industrial processes, which can effectively collect particles in the submicrometre range, is limited to the electrostatic precipitator and bag filter as cost effective methods. To meet ever decreasing emission levels, demanded by the Regulatory Agencies, the equipment suppliers and academics are involved in ongoing research and development activities in order to obtain a better understanding of the collection process itself, such as to achieve improved performance and, equally importantly, plant reliability and availability. This paper reviews some of the activities in the electrical, microelectronics, material sciences, fluid flow and finite element analysis fields and indicates how the findings are leading to new designs that are more reliable and also how the improvements are making the equipment more cost effective while operating at a higher performance level. Finally, with the concern over the emission of ‘air toxics’, while both the electrostatic precipitator and bag filter are established technology for effectively removing solid and liquid particulates with sizings well below 1 micrometre there is now an additional requirement for collecting vapour phase materials to meet the latest regulatory emission levels. Some ideas and approaches are examined which can prove effective in collecting the majority of materials classified as ‘air toxics’, such that the equipment will meet the existing and possible future emission standards.

scholarly journals Synthesis and Antitumor Evaluation of Novel Bis-Triaziquone Derivatives

Molecules ◽  
2009 ◽  
Vol 14 (7) ◽  
pp. 2306-2316 ◽  
Author(s):  
Cheng Hua Huang ◽  
Hsien-Shou Kuo ◽  
Jia-Wen Liu ◽  
Yuh-Ling Lin
Keyword(s):  
Cell Lines ◽  
Anticancer Agents ◽  
Research Effort ◽  
Normal Skin ◽  
Normal Fibroblast ◽  
Cytotoxic Activities ◽  
Design Synthesis ◽  
Human Carcinoma ◽  
Ongoing Research ◽  
Lc50 Value

Aziridine-containing compounds have been of interest as anticancer agents since late 1970s. The design, synthesis and study of triaziquone (TZQ) analogues with the aim of obtaining compounds with enhanced efficacy and reduced toxicity are an ongoing research effort in our group. A series of bis-type TZQ derivatives has been prepared and their cytotoxic activities were investigated. The cytotoxicity of these bis-type TZQ derivatives were tested on three cancer lines, including breast cancer (BC-M1), oral cancer (OEC-M1), larynx epidermal cancer (Hep2) and one normal skin fibroblast (SF). Most of these synthetic derivatives displayed significant cytotoxic activities against human carcinoma cell lines, but weak activities against SF. Among tested analogues the bis-type TZQ derivative 1a showed lethal effects on larynx epidermal carcinoma cells (Hep2), with an LC50 value of 2.02 mM, and also weak cytotoxic activity against SF cells with an LC50 value over 10 mM for 24 hr treatment. Comparing the viability of normal fibroblast cells treated with compound 1a and TZQ, the LC50 value of the latter was 2.52 mM, indicating more toxicity than compound 1a. This significantly decreased cytotoxicity of compound 1a towards normal SF cells, while still maintaining the anticancer activity towards Hep2 cells is an interesting feature. Among the seven compounds synthesized, compound 1c has similar toxicity effects on the three cancer cell lines and SF normal cells as the TZQ monomer.

Ongoing research protocols for the pharmacological treatment of neuropsychiatric symptoms in dementia

2020 ◽  
pp. 1-9
Author(s):  
M. Canevelli ◽  
G. Remoli ◽  
M. Toccaceli Blasi ◽  
L. Tariciotti ◽  
G. Sarli ◽  
...  
Keyword(s):  
Research Effort ◽  
Neuropsychiatric Symptoms ◽  
Phase 1 ◽  
Research Priorities ◽  
Eligibility Criteria ◽  
Ongoing Research ◽  
Research Activities ◽  
Effective Interventions ◽  
Dementia Research ◽  
Ongoing Phase

The implementation of effective interventions for neuropsychiatric symptoms (NPS) is perceived as one of the most pressing research priorities in the field of dementia and one of the main unmet needs from the perspective of affected individuals and their caregivers and relatives. Nevertheless, to date, only a relatively marginal part of dementia research has focused on NPS. This study aimed to describe and discuss the state of the art concerning the identification and development of new pharmacological treatments for NPS in dementia. A review of 320 ongoing phase 1, 2, 3, and 4 protocols registered in the clinicaltrials.gov database was performed. All the trials enrolling patients with dementia were selected. Only studies adopting clinical measures of NPS frequency and/or severity as primary outcome were retained and analyzed. Overall, only a minority of ongoing phase 1, 2, 3 and 4 protocols on dementia (i.e., 9.0%) is primarily targeting NPS. Most of these studies are adopting a placebo-controlled parallel assignment design, testing oral compounds, and targeting specific NPS (mostly agitation and/or aggression). A total of 3,445 subjects with dementia will tentatively be recruited in these trials. The methodologies adopted in these studies, the characteristics of the tested interventions, the eligibility criteria, and the operational definitions of NPS are presented and discussed. The relevance of NPS is not yet matched by an adequate research effort. The current tendency at privileging disease-modifying approaches and other symptoms of dementia and the methodological complexity of studying NPS are still substantially contributing to the gap between research activities and clinical needs.

scholarly journals RLAM: A Dynamic and Efficient Reinforcement Learning-Based Adaptive Mapping Scheme in Mobile WiMAX Networks

2014 ◽  
Vol 10 (2) ◽  
pp. 173-196 ◽  
Author(s):  
M. Louta ◽  
P. Sarigiannidis ◽  
S. Misra ◽  
P. Nicopolitidis ◽  
G. Papadimitriou
Keyword(s):  
Reinforcement Learning ◽  
Learning Automata ◽  
Base Station ◽  
Research Literature ◽  
Average Error ◽  
Mobile Wimax ◽  
Width Ratio ◽  
Dynamic Adjustment ◽  
Extensive Evaluation ◽  
Improved Performance

WiMAX (Worldwide Interoperability for Microwave Access) constitutes a candidate networking technology towards the 4G vision realization. By adopting the Orthogonal Frequency Division Multiple Access (OFDMA) technique, the latest IEEE 802.16x amendments manage to provide QoS-aware access services with full mobility support. A number of interesting scheduling and mapping schemes have been proposed in research literature. However, they neglect a considerable asset of the OFDMA-based wireless systems: the dynamic adjustment of the downlink-to-uplink width ratio. In order to fully exploit the supported mobile WiMAX features, we design, develop, and evaluate a rigorous adaptive model, which inherits its main aspects from the reinforcement learning field. The model proposed endeavours to efficiently determine the downlink-to-uplinkwidth ratio, on a frame-by-frame basis, taking into account both the downlink and uplink traffic in the Base Station (BS). Extensive evaluation results indicate that the model proposed succeeds in providing quite accurate estimations, keeping the average error rate below 15% with respect to the optimal sub-frame configurations. Additionally, it presents improved performance compared to other learning methods (e.g., learning automata) and notable improvements compared to static schemes that maintain a fixed predefined ratio in terms of service ratio and resource utilization.

EARLY OBSERVATIONS OF ROTOR CLOUDS BY ANDRIJA MOHOROVIČIĆ

2007 ◽  
Vol 88 (5) ◽  
pp. 693-700 ◽  
Author(s):  
Vanda Grubišić ◽  
Mirko Orlić
Keyword(s):  
Research Effort ◽  
Geophysical Research ◽  
Ongoing Research ◽  
Northern Adriatic ◽  
Short Account ◽  
Rotor Experiment ◽  
History Of ◽  
The Subject ◽  
Meteorological Observations ◽  
Rotor Type

This article delivers a short history of the early quantitative documentation of a rotor-type circulation in the bora-type flow on the northern Adriatic by Andrija Mohorovičić, an all-around geophysicist and the father of Croatian geophysical research who is widely known as the discoverer of discontinuity between the Earth's crust and mantle. This historical work presents an overview of Mohorovičić's research technique and rotor-related contributions, together with a short account of other observations of rotors contemporary to Mohorovičić as well as those from the 1920s and 1930s, considered to be seminal work on the subject on atmospheric rotors to date. In the year that marks the 150th anniversary of Mohorovičićs birth, his early meteorological observations remain germane for atmospheric rotor research, which is currently experiencing a renaissance with the Terrain-Induced Rotor Experiment (T-REX), a recently completed international field campaign and an ongoing research effort focused on atmospheric terrain-induced rotors.

Sign in / Sign up

Export Citation Format

Share Document