4101 research outputs found
Sort by
Design and implementation of camera-based security system (CBSS) for detecting missing persons
No full textAn efficient AI-based Camera security system is important for locating missing persons. In simple words, if any suspicious face is detected by the system, it sends an alert to the authorized people. Thus, this eliminates the risk of a certain theft from the organization. The focus in our project is implementing and designing a camera-based security system (CBSS) for locating missing persons. The CBSS system is designed using a high resolution camera for detection and several facial recognition features were implemented in the model. In the end, the experiments of our program showed that the system had a more accurate detection notwithstanding the proximity of detection and in almost all the angular positions of detection
DDoS attack prediction using decision tree and random forest algorithms
No full textThe most common network attacks are Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks which causes packet loss by delaying the exchange of information, thereby altering the data packets sent through networks which affect the integrity and reliability of the data. Over time, various machine learning models have been identified and presented by researchers to predict and prevent DoS and DDoS attacks. Many researchers have proposed and used different machine learning techniques to predict DoS and DDoS attacks, however, there is still a need for improvement in the accuracy of prediction and more evaluation of these algorithms and a need for more algorithms to be explored. Hence, this paper improves on existing works by re-evaluating and comparing the accuracy between Decision Tree and Random Forest Algorithms in predicting DDoS attacks. The results of the paper show that Random Forest (RF) Regression model is the best-fit model for the cleaned DDoS SDN dataset used because it is more accurate as it has a lesser mean squared error of 0.21091041940417007 for the test data compared to the mean squared error value of Decision Tree Regression (DTR) Model. Hence, the paper concludes that the RF model is the best-fit model to be used in predicting DDoS attacks. However, the paper proposes that more machine learning algorithms should be explored, implemented, and re-evaluated in detecting DDoS attacks
Colour trend analysis using machine learning and histogram
No full textA significant aspect of colour prediction is the process of detecting a colour palette that represents a collection at a fashion show. People do this manually, but often with too many images, it becomes a hard task. An automated machine-learning method has been developed to generate colour palettes for fashion shows. the model was obtained by fashion pictures dataset, representing each of 48 images of her from a particular fashion show. This work can be extended to analyse millions of images from social media feeds and provide data driven insights for colour prediction
Fraud detection using decision tree algorithm to curb identity theft
No full textIdentity theft is a growing concern that can cause significant financial and emotional harm to individuals. One way to detect and prevent identity theft is by using machine learning algorithms, such as decision tree. In this study, we investigate the effectiveness of using a decision tree algorithm in detecting and preventing identity theft. A dataset consisting of personal information, as well as information on suspicious activity, was collected from a financial institution. The dataset included a total of 284807 rows of data and 30 columns. The decision tree algorithm was implemented using the Python programming language and the scikit-learn library. The algorithm was trained on the training set and used to classify new cases as either fraudulent or non-fraudulent. The performance of the decision tree algorithm was evaluated using several performance metrics such as accuracy, precision, recall and F1-score. Results showed that the decision tree algorithm was effective in detecting and preventing identity theft, with an overall accuracy of 99%. These findings demonstrate the potential of using decision tree algorithms in detecting and preventing identity theft, which can help to curb the increasing problem of identity theft and protect individuals from financial and emotional harm
‘Not so Good Vibrations’: Five collaborative autoethnographic accounts of Brian Wilson, his life, music, rock ‘n’ recovery’
No full textThe purpose of this paper is to provide an analysis of the life of the musician Brian Wilson from five different perspectives.The authors used a mixed method of collaborative autoethnography, psychobiography and digital team ethnography to try and better understand the life and contributions of Brian Wilson.Each of the five contributors provides different insights into the life and music of Brian Wilson.While the focus of this paper is on a single individual, a case study, the long and distinguished life of Brian Wilson provides much material for discussion and theorising.Each individual presenting to mental health services has a complex biography. The five different contributions articulated in this paper, could perhaps be taken as similar to the range of professional opinions seen in mental health teams, with each focussing on unique but overlapping aspects of the person’s story.This account shows the importance of taking a biological-psychological-social-spiritual and cultural perspective on mental illness.This multi-layered analysis brings a range of perspectives to bear on the life and achievements of Brian Wilson, from developmental, musical, psychological, and lived experience standpoints
Development of a conceptual framework for strategic implementation of health, safety and environmental management in the UAE construction industry
No full textThe study critically evaluates strategic implementation of health and safety (H&S) and its effect on Environmental Management in the United Arab Emirates (UAE) construction industry. Previous research indicates that the construction industry, while improving its injury rates, is not making up sufficient ground on all industry-specific average performances. In a modernising construction industry, it must be asked why there is no bold commitment to lowering these rates by high percentages? Perhaps it is time for responsible authorities to step up and do their job. Construction workers comprise a significant percentage of the Gulf Cooperation Council’s (GCC) migrant workforces. The study adopted mixed research methods. Qualitative data collected were analysed using thematic analysis has been performed for qualitative data collected by six interviews, and for the quantitative approach in a survey of 106 UAE construction professionals and has been conducted to support the findings.The findings indicate that reviews and audits and evaluations are integral for projects to sustain their specialist competence. These mechanisms assist project heads in navigating the evolving landscape of the industry by leveraging accumulated expertise. Traditional engineering guidance seems insufficient for today's construction project overseers. Construction project outcomes are often gauged by work efficiency, which gets swayed by the effectiveness of construction practices. Given the labour centric nature of construction, the workforce emerges as a primary asset. Common challenges include a lack of clarity and executing tasks in an unordered manner, which can impede construction effectiveness. Reward structures appear to have a positive influence on job contentment, organizational allegiance, and worker output. Tech-driven solutions have been embraced to bolster workplace safety and enhance service standards. Boosting service excellence involves refining operations and sidestepping missteps
Effective house price prediction using machine learning
No full textIn recent times, there have been a surge in the housing business, such that prediction of houses is of utmost important both for the seller and the potential buyer. This has been influenced by several key indices. Many approaches have been used to tackle the issue of predicting house prices to help the house owners and real estate agents maximise their profit while the prospective buyers make better informed decision. This study focuses on building an effective model for the prediction of house prices. Since price is a continuous variable, it was expedient we used regression models. Some regression models like linear regression, Random Forest regressor (RF), Extreme Gradient Boosting Regressor (XGBoost), Support Vector Machine (SVM) regressor, K-Nearest Neighbor (KNN) and Linear regression were employed. The result showed that Random Forest Regressor showed a superior performance having an R2 score of 99.97% while SVM regressor performed poorly with an R2 score of −4.11%. The result proved that Random Forest regressor as an effective machine learning model to predicting house prices
Assessing the Potential of Hybrid-Based Metaheuristic Algorithms Integrated with ANNs for Accurate Reference Evapotranspiration Forecasting
No full textEvapotranspiration (ETo) is one of the most important processes in the hydrologic cycle, with specific application to sustainable water resource management. As such, this study aims to evaluate the predictive ability of a novel method for monthly ETo estimation, using a hybrid model comprising data pre-processing and an artificial neural network (ANN), integrated with the hybrid particle swarm optimisation-grey wolf optimiser algorithm (PSOGWO). Monthly data from Al-Kut City, Iraq, over the period 1990 to 2020, were used for model training, testing, and validation. The predictive accuracy of the proposed model was compared with other cutting-edge algorithms, including the slime mould algorithm (SMA), the marine predators algorithm (MPA), and the constriction coefficient-based particle swarm optimisation and chaotic gravitational search algorithm (CPSOCGSA). A number of graphical methods and statistical criteria were used to evaluate the models, including root mean squared error (RMSE), Nash-Sutcliffe model efficiency (NSE), coefficient of determination (R-2), maximum absolute error (MAE), and normalised mean standard error (NMSE). The results revealed that all the models are efficient, with high simulation levels. The PSOGWO-ANN model is slightly better than the other approaches, with an R-2 = 0.977, MAE = 0.1445, and RMSE = 0.078. Due to its high predictive accuracy and low error, the proposed hybrid model can be considered a promising technique
Listening to other people's traumatic experiences: What makes it hard and what could protect professionals from developing related distress? A qualitative investigation
No full textListening to people talk about their trauma experiences involves indirect exposure to trauma (IET) and can trigger emotional distress. Existing studies about the risk factors for post-IET distress have methodological limitations and reported inconsistent results, making their findings difficult to meaningfully synthesise. Also, most of them did not focus explicitly on trauma narratives and did not explore qualitatively the opinions and experiences of professionals who work closely with trauma survivors. The present study involved 36 professionals who worked with trauma survivors and used a qualitative design to investigate: (a) the perceived impact of the survivors' accounts, (b) the factors they deemed as important to be psychologically prepared for trauma accounts, and (c) their strategies for coping with IET. The semi-structured interviews conducted yielded rich data that was analysed thematically and organised in 13 subordinate themes, and 4 master themes. Listening to trauma narratives was thought to lead to emotional distress when it challenges the listener's ‘basic assumptions’ of safety and justice, when the listener has reduced sense of control and operates outside their ‘window of tolerance’, when empathic responses are too strong, and psychological preparedness for trauma-narratives is perceived as insufficient. Recommendations for future research and implications for practice are discussed
Turqoise DP bag
No full textOver the past two years I have observed with increasing fascination the growing number of discarded dog shit bags (ddsbs) I encounter whilst out walking in both open countryside, urban parklands and even suburban streets. This has led to a great deal of speculative thought on my part as to why this situation has developed.I can fully understand dog owners simply ignoring their dogs output (unpleasant as it is for anyone who encounters it with all its negative health associations) as it will in a relatively short time biodegrade and essentially disappear. I can also appreciate dog owners who scoop and bag dog mess and place it in a bin for disposal. What I fail to understand is the increasing number of dog owners who bag their dog's mess and then discard in bushes or hang on fences/tree branches or leave in the middle of pathways and playing fields. Is this purely about not wishing to be fined and thereby picking the right moment to surreptitiously dispose of the offending article? Whatever the reasoning the ddsb has very quickly become a feature of our environment.The images presented here become typologies that reflect on the nature of function and style and confront the viewer with the (often unseen) contents of the bags leading to a mixture of amusement, bemusement, curiosity and revulsion.John Darwel