scholarly journals A Novel YOLOv3 Algorithm-Based Deep Learning Approach for Waste Segregation: Towards Smart Waste Management

Electronics ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 14
Author(s):  
Saurav Kumar ◽  
Drishti Yadav ◽  
Himanshu Gupta ◽  
Om Prakash Verma ◽  
Irshad Ahmad Ansari ◽  
...  
Keyword(s):  
Deep Learning ◽  
Waste Management ◽  
Organic Waste ◽  
Learning Strategy ◽  
Smart Cities ◽  
Learning Approach ◽  
Generalization Capability ◽  
Novel Approach ◽  
Waste Segregation ◽  
Glass Metal

The colossal increase in environmental pollution and degradation, resulting in ecological imbalance, is an eye-catching concern in the contemporary era. Moreover, the proliferation in the development of smart cities across the globe necessitates the emergence of a robust smart waste management system for proper waste segregation based on its biodegradability. The present work investigates a novel approach for waste segregation for its effective recycling and disposal by utilizing a deep learning strategy. The YOLOv3 algorithm has been utilized in the Darknet neural network framework to train a self-made dataset. The network has been trained for 6 object classes (namely: cardboard, glass, metal, paper, plastic and organic waste). Moreover, for comparative assessment, the detection task has also been performed using YOLOv3-tiny to validate the competence of the YOLOv3 algorithm. The experimental results demonstrate that the proposed YOLOv3 methodology yields satisfactory generalization capability for all the classes with a variety of waste items.

scholarly journals Deep Learning for Transient Image Reconstruction from ToF Data

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1962
Author(s):  
Enrico Buratto ◽  
Adriano Simonetto ◽  
Gianluca Agresti ◽  
Henrik Schäfer ◽  
Pietro Zanuttigh
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Light Response ◽  
Real Data ◽  
Depth Image ◽  
Learning Approach ◽  
Multiple Reflections ◽  
Noisy Input ◽  
Novel Approach ◽  
Incoming Light

In this work, we propose a novel approach for correcting multi-path interference (MPI) in Time-of-Flight (ToF) cameras by estimating the direct and global components of the incoming light. MPI is an error source linked to the multiple reflections of light inside a scene; each sensor pixel receives information coming from different light paths which generally leads to an overestimation of the depth. We introduce a novel deep learning approach, which estimates the structure of the time-dependent scene impulse response and from it recovers a depth image with a reduced amount of MPI. The model consists of two main blocks: a predictive model that learns a compact encoded representation of the backscattering vector from the noisy input data and a fixed backscattering model which translates the encoded representation into the high dimensional light response. Experimental results on real data show the effectiveness of the proposed approach, which reaches state-of-the-art performances.

scholarly journals A deep learning approach to capture the essence of Candida albicans morphologies

2021 ◽  
Author(s):  
Van Bettauer ◽  
Anna CBP Costa ◽  
Raha Parvizi Omran ◽  
Samira Massahi ◽  
Eftyhios Kirbizakis ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Strategy ◽  
Developmental Trajectories ◽  
Generative Adversarial Networks ◽  
Learning Approach ◽  
Adversarial Networks ◽  
Latent Space ◽  
Contrast Microscopy ◽  
Opportunistic Human Pathogen ◽  
Community Meeting

We present deep learning-based approaches for exploring the complex array of morphologies exhibited by the opportunistic human pathogen C. albicans. Our system entitled Candescence automatically detects C. albicans cells from Differential Image Contrast microscopy, and labels each detected cell with one of nine vegetative, mating-competent or filamentous morphologies. The software is based upon a fully convolutional one-stage object detector and exploits a novel cumulative curriculum-based learning strategy that stratifies our images by difficulty from simple vegetative forms to more complex filamentous architectures. Candescence achieves very good performance on this difficult learning set which has substantial intermixing between the predicted classes. To capture the essence of each C. albicans morphology, we develop models using generative adversarial networks and identify subcomponents of the latent space which control technical variables, developmental trajectories or morphological switches. We envision Candescence as a community meeting point for quantitative explorations of C. albicans morphology.

Hybrid Deep Learning Approach for Efficient Outdoor Parking Monitoring in Smart Cities

2021 ◽  
pp. 463-474
Author(s):  
Alberto Tellaeche Iglesias ◽  
Iker Pastor-López ◽  
Borja Sanz Urquijo ◽  
Pablo García-Bringas
Keyword(s):  
Deep Learning ◽  
Smart Cities ◽  
Learning Approach

scholarly journals Urban Waste as a Resource: The Case of the Utilisation of Organic Waste to Improve Agriculture Productivity Project in Accra, Ghana

2020 ◽  
pp. 123-145
Author(s):  
Dzidzo Yirenya-Tawiah ◽  
Ted Annang ◽  
Benjamin Dankyira Ofori ◽  
Benedicta Yayra Fosu-Mensah ◽  
Elaine Tweneboah- Lawson ◽  
...  
Keyword(s):  
Waste Management ◽  
Value Chain ◽  
Organic Waste ◽  
Solid Waste Management ◽  
Lessons Learned ◽  
Municipal Solid Waste Management ◽  
Key Stakeholders ◽  
Management Processes ◽  
Waste Segregation ◽  
Municipal Assembly

AbstractPoor municipal solid waste management continues to be a daunting issue for municipal authorities in Ghana. Major cities generate 2000 tonnes of mixed municipal waste per day, of which about 80% is collected and disposed of at open dump sites and/or at the limited number of landfills available. About 60% of this waste is organic. The Utilization of Organic Waste to Improve Agricultural Productivity (UOWIAP) project sought to co-create knowledge through a private-public engagement for the development of organic waste value chain opportunities to sustainably manage municipal organic waste and, at the same time, improve urban farm soils and increase food productivity in the Ga-West Municipal Assembly in the Greater Accra Region of Ghana. Through the project, identified key stakeholders in the waste and agricultural sectors, such as market traders, informal waste collectors, unemployed persons, farmers, landscapers, media, agricultural extension officers, Municipal Assembly officers and the general public, were engaged and made aware of sustainable organic waste management processes, including organic waste segregation from source, collection and compost production. Four formal markets were selected for the piloting of organic waste segregation from source. Interested persons were trained in organic waste collection, compost production and entrepreneurship. The lessons learned draw attention to the need for a massive effort to generate demand for compost use as this will invariably drive removal of organic waste from the unsorted waste stream.

scholarly journals Random CNN Structure – Tool to Increase Generalization Ability in Deep Learning

2021 ◽  
Author(s):  
Bartosz Swiderski ◽  
Stanislaw Osowski ◽  
Grzegorz Gwardys ◽  
Jaroslaw Kurek ◽  
Monika Slowinska ◽  
...  
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Quality Measures ◽  
Activation Function ◽  
Small Population ◽  
Generalization Capability ◽  
Average Quality ◽  
Novel Approach ◽  
Learning Data ◽  
Nonlinear Activation Function

Abstract The paper presents a novel approach to designing the CNN structure of improved generalization capability in the presence of a small population of learning data. In contrast to the classical methods for building CNN, we propose to introduce some randomness in the choice of layers with a different type of nonlinear activation function. Image processing in these layers is performed using either the ReLU or the softplus function. This choice is random. The randomness introduced into the network structure can be interpreted as a special form of regularization. Experiments performed in the recognition of images belonging to either melanoma or non-melanoma cases have shown a significant improvement in the average quality measures, such as the accuracy, sensitivity, precision, and the area under the ROC curve.

scholarly journals In Search of Intellectual Stimulation: Understanding the Relationship Between Motivation, Deep Learning and Stimulation in the Higher Education Classroom

2017 ◽  
Vol 5 (1) ◽  
pp. 9-29
Author(s):  
Sandeep Chowdhry ◽  
Renata Osowska
Keyword(s):  
Higher Education ◽  
Deep Learning ◽  
Learning Styles ◽  
Classroom Environment ◽  
Teaching And Learning ◽  
Engineering Students ◽  
Learning Strategy ◽  
Learning Approach ◽  
Intellectual Stimulation ◽  
Student Survey

One of the key educational notions measured in the National Student Survey (NSS) is intellectual stimulation. This study aimed to find out Higher Education (HE) engineering students’ views of intellectual stimulation with a focus on its measurement and supporting its increase within the classroom environment. A quantitative questionnaire acted as a data gathering instrument. The sample comprised 128 students from Edinburgh Napier University (ENU), Scotland. The survey findings showed a positive correlation and positive agreement between the intellectual stimulation (IS), intrinsic motivation (IM) and deep learning approach (DLA) scales. The students’ feedback suggests that implementation of the new intellectual scale based teaching and learning strategy is useful in intellectually stimulated the students and encouraged them to adopt deep learning approach. The findings suggest the design of an intellectually stimulating environment in HE classroom, should consider students’ learning styles, challenge students, allow the provision of timely feedback and provide opportunities to encourage independent thought. Further, the research suggests, the studied institution should encourage staff to consider the intellectual stimulation scale when constructively aligning learning and teaching with an assessment.

Sign in / Sign up

Export Citation Format

Share Document