scholarly journals WATER TEMPERATURE MONITORING IN EASTERN CANADA: A CASE STUDY FOR NETWORK OPTIMIZATION

2018 ◽  
Author(s):  
ANDRÉ ST-HILAIRE ◽  
CLAUDINE BOYER ◽  
NORMAND BERGERON ◽  
ANIK DAIGLE
Keyword(s):  
Water Temperature ◽  
Network Optimization ◽  
Temperature Monitoring ◽  
Eastern Canada

scholarly journals Investigating the Potential of Network Optimization for a Constrained Object Detection Problem

2021 ◽  
Vol 7 (4) ◽  
pp. 64
Author(s):  
Tanguy Ophoff ◽  
Cédric Gullentops ◽  
Kristof Van Beeck ◽  
Toon Goedemé
Keyword(s):  
Computational Complexity ◽  
Object Detection ◽  
Network Optimization ◽  
Real Life ◽  
Optimization Techniques ◽  
Training Data ◽  
Single Shot ◽  
Standard Object ◽  
Number Of Classes

Object detection models are usually trained and evaluated on highly complicated, challenging academic datasets, which results in deep networks requiring lots of computations. However, a lot of operational use-cases consist of more constrained situations: they have a limited number of classes to be detected, less intra-class variance, less lighting and background variance, constrained or even fixed camera viewpoints, etc. In these cases, we hypothesize that smaller networks could be used without deteriorating the accuracy. However, there are multiple reasons why this does not happen in practice. Firstly, overparameterized networks tend to learn better, and secondly, transfer learning is usually used to reduce the necessary amount of training data. In this paper, we investigate how much we can reduce the computational complexity of a standard object detection network in such constrained object detection problems. As a case study, we focus on a well-known single-shot object detector, YoloV2, and combine three different techniques to reduce the computational complexity of the model without reducing its accuracy on our target dataset. To investigate the influence of the problem complexity, we compare two datasets: a prototypical academic (Pascal VOC) and a real-life operational (LWIR person detection) dataset. The three optimization steps we exploited are: swapping all the convolutions for depth-wise separable convolutions, perform pruning and use weight quantization. The results of our case study indeed substantiate our hypothesis that the more constrained a problem is, the more the network can be optimized. On the constrained operational dataset, combining these optimization techniques allowed us to reduce the computational complexity with a factor of 349, as compared to only a factor 9.8 on the academic dataset. When running a benchmark on an Nvidia Jetson AGX Xavier, our fastest model runs more than 15 times faster than the original YoloV2 model, whilst increasing the accuracy by 5% Average Precision (AP).

scholarly journals Analisis Kondisi Kualitas Air Pada Budidaya Ikan Kerapu Tikus (Cromileptes altivelis) Di Situbondo [Analysis Of Water Quality Conditions On Humpback Grouper Culture (Cromileptes altivelis) In Situbondo]

2019 ◽  
Vol 5 (1) ◽  
pp. 1
Author(s):  
Ervany Eshmat N, Abdul Manan
Keyword(s):  
Water Quality ◽  
Dissolved Oxygen ◽  
Water Temperature ◽  
Economic Value ◽  
International Markets ◽  
Fish Culture ◽  
Quality Analysis ◽  
Local Market ◽  
Descriptive Method

Abstract The humpback grouper (Cromileptes altivelis) is one of the fishery commodities with high economic value in both local and international markets. The price of humpback grouper can reach Rp. 200,000 - Rp. 400,000 / kilogram in the local market. The humpback grouper is potentially to be developed in most coastal areas of Indonesia. The conditions of water quality have a very important role for the success of fish culture of humpback grouper. To that end, monitoring and management of water quality are necessary in fish culture. The purpose of this case study is to determine the water quality conditions on humpback grouper culture in BBAP, Situbondo. The study was conducted on 16 January until 16 February 2012. The study method use descriptive method. From the results of water quality analysis, the water in humpback grouper broodstock ponds (I1 and I2) is no smell, no colour water, temperature 26.1-30 oC, salinity 27-35 ppt, dissolved oxygen 3.3-3.9 ppm, ammonia levels <0.001-0.22 ppm, nitrite levels 0.0075-0.085 ppm, alkalinity 110-120 ppm and pH 7.94-8.18. The water in humpback grouper hatchery ponds (B1 and B2) is no smell, green colour water, temperature 26.7-29.3 oC, salinity 27-34 ppt, dissolved oxygen 2.7-3.7 ppm, ammonia levels 0.0781-0.28 ppm, nitrite levels 0.0225-3.3305 ppm, alkalinity 94-126 ppm, and pH 7.14-7.81.

Canadian Rural Youth and Role Tension of the Police: ‘It’s Hard in a Small Town’

Youth Justice ◽  
2019 ◽  
Vol 20 (3) ◽  
pp. 199-214
Author(s):  
Rosemary Ricciardelli ◽  
Michael Adorjan ◽  
Dale Spencer
Keyword(s):  
Police Officers ◽  
Rural Areas ◽  
Rural Youth ◽  
Eastern Canada ◽  
Group Discussions ◽  
Resource Officers ◽  
Pros And Cons ◽  
Youth Perceptions ◽  
And Gender

This article presents findings from a case study examining youth perceptions of the police in rural areas of Eastern Canada. A total of 20 semistructured focus group discussions were conducted with 60 youth from Canadian rural Atlantic areas, who were purposively recruited, with groups stratified by age and gender. Discussions centered on role tension regarding the police’s role, that is, along a continuum between law enforcement and public protection versus community policing and crime prevention. Our discussions highlight the arguably ironic view that it is harder to maintain trust when there are strong personal relations with the police. Discussions highlight the ‘pros and cons’ of informal familiarity with police officers, especially the presence of school resource officers and policing in the context of monitoring youth on modes of transportation germane to rural Atlantic Canada (i.e. skidoos). Implications from this study suggest that when dealing with youth, identifying and addressing youth perceptions of the police role can help improve police–youth interactions.

Development of Zonal-Specific Semivariograms for a Strategic RWIS Network Optimization: Case Study

2019 ◽  
Vol 25 (2) ◽  
pp. 05019004
Author(s):  
Tae J. Kwon ◽  
Matthew Muresan ◽  
Liping Fu ◽  
Taimur Usman
Keyword(s):  
Network Optimization

Management strategies for spasmodic stocks: a Canadian Atlantic redfish fishery case study

2020 ◽  
Vol 77 (4) ◽  
pp. 684-702
Author(s):  
Roberto Licandeo ◽  
Daniel E. Duplisea ◽  
Caroline Senay ◽  
Julie R. Marentette ◽  
Murdoch K. McAllister
Keyword(s):  
Inventory Management ◽  
Management Strategy ◽  
Management Strategies ◽  
Trawl Survey ◽  
Eastern Canada ◽  
Strategy Evaluation ◽  
Management Procedures ◽  
Harvest Control Rule ◽  
Sebastes Mentella

There exist few recommendations for managing stocks with spasmodic recruitment, despite such stocks being not uncommon. Management procedures (MPs), developed for two species of redfish (Sebastes mentella and Sebastes fasciatus) in eastern Canada, are recommended for setting catch limits during periods of high and low abundance. A well-designed fishery-independent trawl survey is essential to provide advance warning of strong recruitment events and project future recruitment. Under an “inventory management” strategy, a more appropriate aim in spasmodic stocks may be to maximize the number of years with “good catches,” instead of maximizing total catches, as is traditionally considered in management strategy evaluation (MSE). Following a spasmodic recruitment event, an empirical harvest control rule based on larger fish delays the harvest of large cohorts by a few years, targets more commercially valuable fish sizes, and reduces the risk of growth overfishing. Capped MPs produced longer periods of large catches than uncapped MPs. MPs allowed for low harvests during periods of low abundance, thus avoiding unnecessary hardship in the industry. MPs evaluated here could be good candidates for other stocks with similar or less extreme recruitment variability.

Sign in / Sign up

Export Citation Format

Share Document