2821 research outputs found
Sort by
PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment
Full text linkFruits significantly impact everyday living, i.e., Citrus fruits. Numerous fruits have a solid nutritious value and are packed with multivitamins and trace components. Citrus fruits are delicate and susceptible to many diseases and infections. Many researchers have suggested deep and machine learning-based fruit disease detection and classification models. This research presents a precise fruit disease identification model based on context data fusion with Faster-CNN in an edge computing environment. The goal is to develop an accurate, efficient, and trustable fruit disease detection model, a critical component of autonomous food production in a robotic edge platform. This research examines and explores four different diseases of Citrus fruits using CNN deep learning models to be adopted as edge computing solutions. Identification of citrus diseases such as cankers black spot, greening, scab, melanosis, and healthy citrus fruits are implemented using the proposed sequential model without pruning, with pruning having different sparsity levels followed by post quantization. Through the transfer learning method, this model is optimized for the assignment of fruit disease detection employing visuals from two patterns: Near-infrared (NIFR) and RGB. Early and late data fusion techniques for integrating multi-model (NIFR and RGB) facts are evaluated. The accuracy obtained from the proposed model for the canker disease is 97%, scab 95%, melanosis 99%, Greening 97%, Black spot 97% and healthy 97%. In this paper, the results of the proposed model are compared and evaluated with the sparsity levels of 50–80%, 60–90%, 70–90%, and 80–90% pruning and also obtained the results of post-quantization on each level. The results show that the model size with 60–90% pruning can be counteracted to the 47.64 of the baseline model without significant loss of accuracy. Moreover, post-quantization can reduce the 60–90% pruning from 28.16 to 8.72. In addition to enhanced precision, the above initiative is much faster to implement for new fruit diseases because it needs bounding box annotation instead of pixel-level annotation
Teacher vulnerability in teacher identity in times of unexpected social change
Full text linkThe COVID-19 pandemic brought unexpected challenges to
the lives and professional practice of teachers regardless of
their institutional context. Our understanding of how teachers viewed their impact on their perceived sense of professional identity is largely unexplored, especially concerning
teachers working in the post-compulsory sector. This article
discusses the findings from a small-scale qualitative research
project that aimed to investigate, `what teachers’ reflective
stories tell us about their perceptions of their professional
identities in times of unexpected social change.’ To explore
how teachers perceived their professional roles in these
challenging times we used a reflective narrative approach
in the format of McAdams’s life-story interview (1993). Seven
volunteer participants who formed a purposive sample of
professionals from a variety of post-compulsory education
institutions in the UK were asked to describe key episodes to
capture their experiences covering the period from
March 2020 to the end of May 2021. The findings focused
on how unexpected social changes impacted on teachers’
perceived sense of professional identity, specifically through
their sense of vulnerability. Three main themes were identified: vulnerability resulting from questioning professional
credibility; vulnerability in the changing dynamics of relationship development; and vulnerability in the pastoral rol
A vision transformer approach for traffic congestion prediction in urban areas
Full text linkTraffic problems continue to deteriorate because of the increasing population in urban areas that rely on many modes of
transportation, the transportation infrastructure has achieved considerable strides in the last several decades. This has led to an
increase in congestion control difficulties, which directly affect citizens through air pollution, fuel consumption, traffic law breaches,
noise pollution, accidents, and loss of time. Traffic prediction is an essential aspect of an intelligent transportation system in smart cities
because it helps reduce traffic congestion. This article aims to design and enforce a traffic prediction scheme that is efficient and
accurate in forecasting traffic flow. Available traffic flow prediction methods are still unsuitable for real-world applications. This fact
motivated us to work on a traffic flow forecasting issue using Vision Transformers (VTs). In this work, VTs were used in conjunction with
Convolutional neural networks (CNNs) to predict traffic congestion in urban spaces on a city-wide scale. In our proposed architecture, a
traffic image is fed to the CNN, which generates feature maps. These feature maps are then fed to the VT, which employs the dual
techniques of tokenization and projection. Tokenization is used to convert features into tokens containing Vision information, which are
then sent to projection, where they are transformed into feature maps and ultimately delivered to LSTM. The experimental results
demonstrate that the vision transformer prediction method based on Spatio-temporal characteristics is an excellent way of predicting
traffic flow, particularly during anomalous traffic situations. The proposed technology surpasses traditional methods in terms of
precision, accuracy and recall and aids in energy conservation. Through rerouting, the proposed work will benefit travellers and reduce
fuel use
Sentiment computation of UK-originated COVID-19 vaccine tweets: a chronological analysis and news effect
Full text linkThis study aimed to analyse public sentiments of UK-originated tweets related to COVID-19 vaccines, and it applied six chronological time periods, between January and December 2021. The dates were related to six BBC news reports about the most significant developments in the three main vaccines that were being administered in the UK at the time: Pfizer-BioNTech, Moderna, and Oxford-AstraZeneca. Each time period spanned seven days, starting from the day of the news report. The study employed the bidirectional encoder representations from transformers (BERT) model to analyse the sentiments in 4172 extracted tweets. The BERT model adopts the transformer architecture and uses masked language and next sentence prediction models. The results showed that the overall sentiments for all three vaccines were negative across all six periods, with Moderna having the least negative tweets and the highest percentage of positive tweets overall while AstraZeneca attracted the most negative tweets. However, for all the considered time periods, Period 3 (23–29 May 2021) received the least negative and the most positive tweets, following the related BBC report—’COVID: Pfizer and AstraZeneca jabs work against Indian variant’—despite reports of blood clots associated with AstraZeneca during the same time period. Time periods 5 and 6 had no breaking news related to COVID vaccines, and they reflected no significant changes. We, therefore, concluded that the BBC news reports on COVID vaccines significantly impacted public sentiments regarding the COVID-19 vaccines
Andrew Voyce: A living tribute. “You can end up in a happy place.”
Full text linkThe main aim of this paper is to provide a Living Tribute of lived expert by experience and researcher Andrew Voyce.
Andrew provided Jerome with a list of names of people he might approach to write a tribute on his behalf.
The accounts describe the influence that Andrew has had both as an educator and as a trusted colleague for the people approached.
In many ways the voices of people with mental health problems have been marginalised. Few mental health journals, with only some exceptions, encourage lived experience contributions.
The mental health agenda continues to be dominated by professional groups. The remarkable individuals who continually battle with serious mental illness are often lost in official discourses.
Despite the fact that the topic of mental health is now much more in the public domain, research tells us that the most effective anti-stigma strategy is contact with sufferers.
The archivist Dr Anna Sexton co-produced one of the few mental health archives that only featured people with lived experience. Andrew was one of four people featured in it. This account ‘showcases’ the work of this remarkable man
Innovation and digital transformation in local communities
No full textThe use of technology is inevitable in a society of knowledge, being implemented including
at the level of local governments where has the potential to improve interactions between
local authorities and citizens through the simplification of procedures, as well as
contributing to open local government. The innovation and digital transformation of
government means the further modernisation of public administration, seamless cross-border mobility and enhanced digital interactions. The paper aim is to show that local
governments operate in an increasingly open and receptive manner by using innovation
and an increasing number of digital tools that facilitate the development of local
communities and the improvement of living standards
Restructuring priorities: rethinking economic growth for a more active future
Full text linkPhysical inactivity is among the most formidable public health challenges of our time. The World Health Organization recently revealed
that physical inactivity is on the rise and predicted that globally, there
will be around 500 million new cases of preventable non-communicable
diseases between 2020 and 2030 if physical inactivity levels remain as
they are. But why? What’s driving this formidable public health challenge? In this commentary article, I illustrate how the continual pursuit of economic growth is a key driver underpinning physical
inactivity at the population level. I contend that if the priority really is
to address physical inactivity at the population level, then the metrics
we use to define social progress will need recalibratin
Sustainable climatic metrics determination with ensemble predictive analytics
Full text linkSustainability depends upon some major
climate factors which play a major role in ensuring and
assuring that sustainability would be maintained if the
range of safe values of parameters are maintained.
Linear regression and random forest are few among the
machine learning models that were employed in order to
determine the dependency of each factor on
sustainability. The climate data from Delhi from 1971 to
2020 is utilized for the study considering the variables
like temperature, precipitation, humidity and
atmospheric carbon dioxide concentration which were
collected from various authorized sources such as the
Indian Meteorological Department and the Central
Pollution control board. After studying various factors
involved in determining climate sustainability we found
out that temperature and atmospheric carbon dioxide
concentration have the greatest impact with a
percentage of 45% and 30% respectively. Sectors like
agriculture, forestry, energy and water management are
majorly dependent on these key deciding factors. The R
square value was determined to be 0.86 and 0.82
respectively for machine learning models implemented.
We found that the random forest model had a better
score in comparison to the linear regression model. With
this study we thus found out that, how machine learning
models can be trained and tested in order to predict the
future outcomes for sustainability. This study
demonstrates the importance of climate monitoring for
maintaining sustainability
Research ethics in Sub-Saharan Africa: uncovering graduate business students’ attitudes and beliefs which inform approaches toward research ethics
Full text linkTransnational education has grown rapidly in recent years, but the policies and procedures
embedded within Western universities may not adequately reflect the environment in which
students study and conduct research.
This thesis explores the beliefs and attitudes towards research ethics among graduate
students in the two south-central African countries of Zambia and Malawi. The participants
were ten mid-career professionals studying graduate business programs delivered in-country
in partnership with a British university; as part of their programme they were required to
undertake their own primary research project.
By undertaking a qualitative study of students in the region, it uncovers a complex multi-layered ethical system, which includes traditional sources, oral traditions, village uncles, and
indigenous religious sources, alongside Western-centric missionary religions, and the formal
processes such as those advocated by their professions and University ethics processes. Each
of these informs the students’ approaches, often resulting in traditional cultural attitudes
towards ethics sitting uneasily alongside contemporary ethical views. This can make the
formal research ethics processes used by Western universities operating in the region appear
overly strict and inflexible to students leading to tensions between what they are required to
do by the university and what they believe is right.
The growth of transnational education necessitates the investigation of approaches that make
research ethics processes more flexible without removing the ethics approval processes, so
this thesis advocates a culturally adapted research ethics protocol (CAREP) as a model,
bringing regional attitudes to ethics and culture into the research ethics processes through a
continuing dialogic approach. CAREP recognises the impact of cultural factors on an under researched area of education and provides a contribution to the growing debate on ethics in
general and indigenous ethics in particular. It also offers a new perspective on the
decolonisation of universities by recognising the importance of processes as well as the
curriculum.
Adopting a phenomenographic approach, the study uses semi-structured, in-depth qualitative
interviews to consider the students’ views of ethics and the influences that contribute to their
ethical perspective. Their beliefs and attitudes are contrasted with the rigid ethical
compliance required in Western universities. Through rich data, including vivid storytelling,
the participants indicated numerous factors that contributed to their beliefs and attitudes
towards research ethics which are categorised into close social groups, traditional historical
ethics reinforced through storytelling, their religion, their urban versus rural location, and
their beliefs about professionalism
MDROGWL: modified deep reinforcement oppositional wolf learning for group key management in IoT environment
Full text linkSecuring confidential data against unauthorized users leads to access control policies with the rapid progression of Internet of Things (IoT) devices. Because of high mobility subscribers, the dynamic IoT environment is subjected to high signaling overhead which remains a challenging issue to guarantee data dissemination to legitimate users. The group's key management schemes are the central mechanism to deal with dynamic environments. But they are centralized concepts that cause scalability issues and suffer in handling large numbers of subscribers. Therefore, this paper proposes a modified deep reinforcement oppositional wolf learning-based group key management (MDROWL-GKM) system to monitor the data obtained in IoT properly. It does not maximize the network traffic as well as computational overhead when a group member leaves or joins. With the inclusion of an opposition-based learning gray wolf optimization algorithm, the overload issue of the modified deep reinforcement method is eliminated and the performance is enhanced. The efficacy of the proposed MDROWL-GKM system is investigated using different measures namely storage overhead, computation overhead, access response time, space complexity, re-evaluation time, policy adjustment accuracy, and communication overhead. The experimental analysis proves that the proposed MDROWL-GKM system is superior to other state-of-the-art techniques, particularly with high policy adjustment accuracy (96%), less communication overhead (8 μs) and area under curve (AUC) rate (0.982