Pub Date : 2022-11-09DOI: 10.1109/ZCICT55726.2022.10045873
Pavlov Takudzwa Mpinyuri, Edmore Tarambiwa
According to the United Nations Road Safety Performance Review-Zimbabwe report, every 15 minutes, five people die in road accidents within Zimbabwe, recording the highest number of accidents in the SADC region. The situation has brought more pressure and work in the insurance sector as they are expected to process all the claims accurately and timely. Deep learning entails automation, enhancement, analysis, and high accuracy in areas like speech recognition, object detection, and language translation. In this paper, two modern deep learning algorithms MobileNetV2 and DenseNetV121 were used to develop the vehicle damage classification models. The models were used to detect damaged main features of a car, which are: the door, bumper, windscreen, tail lamp, and headlamp. Mobile NetV 2’s53 layers and DenseNet121’s121 layers produced high accuracy rates for identifying damaged parts in vehicles. However, DenseNetV2 produced a higher accuracy of 84& than MobileNetV2, with an accuracy rate of 78%. The models also used low computational resources than the traditional algorithms making them applicable in different insurance companies as they can be easily embedded into client’s mobile phones.
{"title":"Vehicle Damage model classification for Zimbabwe Insurance Sector using MobileNetV2 and DenseNet121","authors":"Pavlov Takudzwa Mpinyuri, Edmore Tarambiwa","doi":"10.1109/ZCICT55726.2022.10045873","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10045873","url":null,"abstract":"According to the United Nations Road Safety Performance Review-Zimbabwe report, every 15 minutes, five people die in road accidents within Zimbabwe, recording the highest number of accidents in the SADC region. The situation has brought more pressure and work in the insurance sector as they are expected to process all the claims accurately and timely. Deep learning entails automation, enhancement, analysis, and high accuracy in areas like speech recognition, object detection, and language translation. In this paper, two modern deep learning algorithms MobileNetV2 and DenseNetV121 were used to develop the vehicle damage classification models. The models were used to detect damaged main features of a car, which are: the door, bumper, windscreen, tail lamp, and headlamp. Mobile NetV 2’s53 layers and DenseNet121’s121 layers produced high accuracy rates for identifying damaged parts in vehicles. However, DenseNetV2 produced a higher accuracy of 84& than MobileNetV2, with an accuracy rate of 78%. The models also used low computational resources than the traditional algorithms making them applicable in different insurance companies as they can be easily embedded into client’s mobile phones.","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129591677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-09DOI: 10.1109/ZCICT55726.2022.10046011
Tshimanga Danny Kazadi, K. Sibanda, Nyashadzashe Tamuka
A smart-home provides a convenient, comfortable secure, and interactive home. The house owner may be able to manage his or her home using a smartphone. Automation systems are increasingly significant and widely adopted in homes to keep improving our quality of life. These systems make it simple and convenient to use household appliances. They provide an innovative way of living in which the homeowner can control his entire house using a smartphone, from turning on a light to unlocking and locking doors; they also provide efficient use of energy. This research created a mobile-based system for home automation. As a methodology, the system was developed using the waterfall model. The model depicts the software development process as a linear and progressive flow. This means that any phase of development can begin only after the previous phase is completed. The simulation methodology was employed during the study for the evaluation of the developed system. Ten trials were carried out to assess the implemented system’s performance. To assess the system’s reliability, the mean-time to failure was utilized. During performance analysis, the study’s system was found to outperform the two other approaches
{"title":"A Mobile-Based Control System For Smart Homes","authors":"Tshimanga Danny Kazadi, K. Sibanda, Nyashadzashe Tamuka","doi":"10.1109/ZCICT55726.2022.10046011","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10046011","url":null,"abstract":"A smart-home provides a convenient, comfortable secure, and interactive home. The house owner may be able to manage his or her home using a smartphone. Automation systems are increasingly significant and widely adopted in homes to keep improving our quality of life. These systems make it simple and convenient to use household appliances. They provide an innovative way of living in which the homeowner can control his entire house using a smartphone, from turning on a light to unlocking and locking doors; they also provide efficient use of energy. This research created a mobile-based system for home automation. As a methodology, the system was developed using the waterfall model. The model depicts the software development process as a linear and progressive flow. This means that any phase of development can begin only after the previous phase is completed. The simulation methodology was employed during the study for the evaluation of the developed system. Ten trials were carried out to assess the implemented system’s performance. To assess the system’s reliability, the mean-time to failure was utilized. During performance analysis, the study’s system was found to outperform the two other approaches","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114873425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-09DOI: 10.1109/ZCICT55726.2022.10045938
Lincoln Chivinge, Leslie Kudzai Nyandoro, Kudakwashe Zvarevashe
Diabetic Retinopathy (DR), chronic progressive disease of the eye, may give rise to permanent sight loss. Clinicians use fundus pictures to check if DR is present and rely on physicians to diagnose the stage or severity by visual inspection of the images. In relying on a clinician’s subjective prognosis, this is deemed a procedure that takes a lot of time and susceptible to misjudgements. In discovering DR, poor Quadratic Weighted Kappa (QWK) scores have resulted from poor quality of pictures and imbalanced distribution of classes. Even though studies have shown high accuracy, sensitivity, specificity and ROC metrics, their limitation is that they do not consider the level of disparity across the classified labels. The QWK score demonstrates that even if an algorithm presents high accuracy, it is still not best fit to classify DR into its 5 classes. Many researchers have tried fine-tuning the neural network to create noise-resistant deep learning and recorded high accuracy and sensitivity but low QWK scores. The problem with the other methods is mainly pre-processing of the images and model building patterns. Most of the studied literature lacks the image augmentation step which might lead to an erroneous result. This research aims to create an algorithm from deep learning models with a data augmentation step and demonstrate how important it is for attaining better QWK scores for all stages of diabetic retinopathy. The model met study objectives and obtained an accuracy of 93% and a QWK score of 0.961. The outcomes show that the method can make accurate predictions without need for human feature extraction and that it may be used as an early DR diagnostic and staging screening tool.
{"title":"Quadratic Weighted Kappa Score Exploration in Diabetic Retinopathy Severity Classification Using EfficientNet","authors":"Lincoln Chivinge, Leslie Kudzai Nyandoro, Kudakwashe Zvarevashe","doi":"10.1109/ZCICT55726.2022.10045938","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10045938","url":null,"abstract":"Diabetic Retinopathy (DR), chronic progressive disease of the eye, may give rise to permanent sight loss. Clinicians use fundus pictures to check if DR is present and rely on physicians to diagnose the stage or severity by visual inspection of the images. In relying on a clinician’s subjective prognosis, this is deemed a procedure that takes a lot of time and susceptible to misjudgements. In discovering DR, poor Quadratic Weighted Kappa (QWK) scores have resulted from poor quality of pictures and imbalanced distribution of classes. Even though studies have shown high accuracy, sensitivity, specificity and ROC metrics, their limitation is that they do not consider the level of disparity across the classified labels. The QWK score demonstrates that even if an algorithm presents high accuracy, it is still not best fit to classify DR into its 5 classes. Many researchers have tried fine-tuning the neural network to create noise-resistant deep learning and recorded high accuracy and sensitivity but low QWK scores. The problem with the other methods is mainly pre-processing of the images and model building patterns. Most of the studied literature lacks the image augmentation step which might lead to an erroneous result. This research aims to create an algorithm from deep learning models with a data augmentation step and demonstrate how important it is for attaining better QWK scores for all stages of diabetic retinopathy. The model met study objectives and obtained an accuracy of 93% and a QWK score of 0.961. The outcomes show that the method can make accurate predictions without need for human feature extraction and that it may be used as an early DR diagnostic and staging screening tool.","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121176977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Detecting early signs of plant leaf diseases is vital in an agrarian economy. Automatic Leaf disease recognition is extremely important because predictive mechanisms that aid in the avoidance of losses can be adopted timeously. Transfer learning algorithms have become a popular solution for recognizing tomato leaf diseases over the years. However, they have innate limitations which include higher processing time and lower accuracy according to various expectations in regards to problem domain. A classification algorithm is as good as the features used to develop the model. Therefore, the primary objective of this experimental study was to discover the most discriminating features in detecting tomato leaf diseases. The paper presents a combination of Grayscale Pixel Value (GPV) features and ResNet9 in an effort to solve the aforementioned problem. We evaluated the proposed solution against other features such as Mean Pixel Value (MPV) and other deep learning generated features. The results showed that our proposed method is effective in detecting tomato leaf diseases because of the significantly low computation time (10 minutes) and superior accuracy (98.59%).
{"title":"Tomato Leaf Diseases Detection with Recommended Prescription Using Deep Learning","authors":"Fredy Chimire, Mbizo Godfrey, Kudakwashe Zvarevashe","doi":"10.1109/ZCICT55726.2022.10045854","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10045854","url":null,"abstract":"Detecting early signs of plant leaf diseases is vital in an agrarian economy. Automatic Leaf disease recognition is extremely important because predictive mechanisms that aid in the avoidance of losses can be adopted timeously. Transfer learning algorithms have become a popular solution for recognizing tomato leaf diseases over the years. However, they have innate limitations which include higher processing time and lower accuracy according to various expectations in regards to problem domain. A classification algorithm is as good as the features used to develop the model. Therefore, the primary objective of this experimental study was to discover the most discriminating features in detecting tomato leaf diseases. The paper presents a combination of Grayscale Pixel Value (GPV) features and ResNet9 in an effort to solve the aforementioned problem. We evaluated the proposed solution against other features such as Mean Pixel Value (MPV) and other deep learning generated features. The results showed that our proposed method is effective in detecting tomato leaf diseases because of the significantly low computation time (10 minutes) and superior accuracy (98.59%).","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126479244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, the COVID-19 pandemic has spread all over the world. Due to its rapid transmission, techniques that automatically detect COVID-19 infections and distinguish it from other forms of pneumonia are crucial. The scientific community has embarked on finding solutions to quick detection of COVID-19 through implementation of deep learning(DL) techniques that can diagnose COVID-19 using computed tomography (CT) lung scans. The use of CT images has been widely accepted in medical imaging and it is a pertinent screening tool due to its higher sensitivity in recognizing early pneumonic changes. Also, most developed DL models developed have been end-to-end from feature extraction to categorization of the COVID19 infected images. The proposed model results showed high accuracy rates on both training and testing of the model in COVID-19 classification. A customised ResNet-50 architecture has the best results in classifying the images and achieved state of art accuracy of 97% on training and testing using the COVID dataset with 200 epochs. This work presented a computationally efficient and highly accurate model for multi-class classification of normal and infected individuals. The model can help in effective early screening of COVID-19 cases hence reducing the burden on healthcare systems.
{"title":"Automatic detection of Covid-19 based on lung CT images using Deep Convolutional Neural Networks (CNN)","authors":"Shawn Mahachi, Kudakwashe Zvarevashe, Leslie Kudzai Nyandoro","doi":"10.1109/ZCICT55726.2022.10045962","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10045962","url":null,"abstract":"In recent years, the COVID-19 pandemic has spread all over the world. Due to its rapid transmission, techniques that automatically detect COVID-19 infections and distinguish it from other forms of pneumonia are crucial. The scientific community has embarked on finding solutions to quick detection of COVID-19 through implementation of deep learning(DL) techniques that can diagnose COVID-19 using computed tomography (CT) lung scans. The use of CT images has been widely accepted in medical imaging and it is a pertinent screening tool due to its higher sensitivity in recognizing early pneumonic changes. Also, most developed DL models developed have been end-to-end from feature extraction to categorization of the COVID19 infected images. The proposed model results showed high accuracy rates on both training and testing of the model in COVID-19 classification. A customised ResNet-50 architecture has the best results in classifying the images and achieved state of art accuracy of 97% on training and testing using the COVID dataset with 200 epochs. This work presented a computationally efficient and highly accurate model for multi-class classification of normal and infected individuals. The model can help in effective early screening of COVID-19 cases hence reducing the burden on healthcare systems.","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114308842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Employee churn is one of the most daunting challenges that an organization is likely to face in its lifecycle. An unexpected employee departure can adversely impact service delivery, reduce productivity and customer loyalty. It is therefore pertinent to predict employee churn to help organizations retain valuable employees. This paper proposes a model that makes use of feature selection through Pearson Correlation Method, Information Gain and the Recursive Feature Elimination together with robust classification methods that include Random Forest (RF), Logistic Regression (LR), Decision Trees (DT), Gradient Boosting Machines (GBM) and K Nearest Neighbors (KNN) to predict employee churn. The training and testing data were obtained from the IBM dataset. The accuracy of the algorithms improved after applying the feature selection methods. Experimental results showed that Random Forest performed better than all the comparative algorithms in terms of classification accuracy. Consequently, the algorithm demonstrated to be a more appropriate algorithm in predicting employee churn.
{"title":"A Supervised Machine Learning Model to Optimize Human Resources Analytics for Employee Churn Prediction","authors":"Vengai Musanga, Edmore Tarambiwa, Kudakwashe Zvarevashe","doi":"10.1109/ZCICT55726.2022.10045987","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10045987","url":null,"abstract":"Employee churn is one of the most daunting challenges that an organization is likely to face in its lifecycle. An unexpected employee departure can adversely impact service delivery, reduce productivity and customer loyalty. It is therefore pertinent to predict employee churn to help organizations retain valuable employees. This paper proposes a model that makes use of feature selection through Pearson Correlation Method, Information Gain and the Recursive Feature Elimination together with robust classification methods that include Random Forest (RF), Logistic Regression (LR), Decision Trees (DT), Gradient Boosting Machines (GBM) and K Nearest Neighbors (KNN) to predict employee churn. The training and testing data were obtained from the IBM dataset. The accuracy of the algorithms improved after applying the feature selection methods. Experimental results showed that Random Forest performed better than all the comparative algorithms in terms of classification accuracy. Consequently, the algorithm demonstrated to be a more appropriate algorithm in predicting employee churn.","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133448332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-09DOI: 10.1109/ZCICT55726.2022.10045922
Estery Shumba, Belinda Mutunhu Ndlovu, S. Nleya, Nesisa Moyo
People have rights to water and sanitation as stated under International Law. It is believed that one billion people in the world lack access to safe drinking water, while two billion have inadequate access to sanitation facilities. Water and sanitation in developing countries face many challenges which hinder the achievement of the Millenium Development Goals and the current Sustainable Development Goals. Even though the Internet of Things (IoT) gained popularity in 2010, its adoption by Zimbabwean local authorities is dawdling. The City of Gweru has been experiencing environmental management problems, waterborne disease outbreaks, serious water shortages, and high-water losses. It is against this background that this study assesses the City of Gweru’s IoT adoption readiness in water and sanitation through the lens of the 5D TDWI IoT readiness assessment model. A positivist research philosophy guided by quantitative data collection methods is used. The results reveal that the City of Gweru’s IoT adoption readiness in water and sanitation is at its preliminary stages and it is established that employees have IoT knowledge as evidenced by their positive attitude towards its adoption. However, the City of Gweru has challenges in the dissemination of vital information to its employees about its ICT policies, goals, and strategic plan.
{"title":"An assessment of Internet of Things (IoT) adoption readiness in water and sanitation in Zimbabwe. A Case of the City of Gweru.","authors":"Estery Shumba, Belinda Mutunhu Ndlovu, S. Nleya, Nesisa Moyo","doi":"10.1109/ZCICT55726.2022.10045922","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10045922","url":null,"abstract":"People have rights to water and sanitation as stated under International Law. It is believed that one billion people in the world lack access to safe drinking water, while two billion have inadequate access to sanitation facilities. Water and sanitation in developing countries face many challenges which hinder the achievement of the Millenium Development Goals and the current Sustainable Development Goals. Even though the Internet of Things (IoT) gained popularity in 2010, its adoption by Zimbabwean local authorities is dawdling. The City of Gweru has been experiencing environmental management problems, waterborne disease outbreaks, serious water shortages, and high-water losses. It is against this background that this study assesses the City of Gweru’s IoT adoption readiness in water and sanitation through the lens of the 5D TDWI IoT readiness assessment model. A positivist research philosophy guided by quantitative data collection methods is used. The results reveal that the City of Gweru’s IoT adoption readiness in water and sanitation is at its preliminary stages and it is established that employees have IoT knowledge as evidenced by their positive attitude towards its adoption. However, the City of Gweru has challenges in the dissemination of vital information to its employees about its ICT policies, goals, and strategic plan.","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133663853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-09DOI: 10.1109/ZCICT55726.2022.10045859
Marvelous Alexander Panganai, Leslie Kudzai Nyandoro, Kudakwashe Zvarevashe
Drowsiness and fatigue are the major reasons for triggering serious and severe road crashes in Zimbabwe and the whole world at large. The developments in technology in recent years brought support and backing to drivers using intelligent automobile systems. Several research studies used datasets of a single driver for training and testing. Some as well used mainly day time images for training and testing the models. Therefore, fatigue and drowsiness is a key possible field of study to prevent numerous number of sleep induced road crashes. In this paper, two methods of feature extraction were proposed which are the MLP (Multilayer - Perceptron), the CNN (Convolutional Neural Network). The PCA (Principal Component Analysis) method was used for dimensionality reduction. Based on these methods, five classifiers where used to detect drowsiness on the driver. The five classifiers used where the LDA, XGBoost, LR, Decision Tree and the K-Nearest neighbors. Experiments were done in order to examine the capacity and usefulness of the approaches contrasted with other techniques. Experimental outcomes demonstrate that the feature extraction technique of CNN provided high accuracy on the five classifiers. The KNN was the average best classifier with a 100% accuracy. Experimental results indicated that the PCA improved the classifiers. This study delivers important and significant answers in practice to curb motor vehicle crashes due to drowsiness.
{"title":"Driver drowsiness detection using Convolutional Neural Networks-inspired features and Principal component analysis with K-Nearest Neighbors","authors":"Marvelous Alexander Panganai, Leslie Kudzai Nyandoro, Kudakwashe Zvarevashe","doi":"10.1109/ZCICT55726.2022.10045859","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10045859","url":null,"abstract":"Drowsiness and fatigue are the major reasons for triggering serious and severe road crashes in Zimbabwe and the whole world at large. The developments in technology in recent years brought support and backing to drivers using intelligent automobile systems. Several research studies used datasets of a single driver for training and testing. Some as well used mainly day time images for training and testing the models. Therefore, fatigue and drowsiness is a key possible field of study to prevent numerous number of sleep induced road crashes. In this paper, two methods of feature extraction were proposed which are the MLP (Multilayer - Perceptron), the CNN (Convolutional Neural Network). The PCA (Principal Component Analysis) method was used for dimensionality reduction. Based on these methods, five classifiers where used to detect drowsiness on the driver. The five classifiers used where the LDA, XGBoost, LR, Decision Tree and the K-Nearest neighbors. Experiments were done in order to examine the capacity and usefulness of the approaches contrasted with other techniques. Experimental outcomes demonstrate that the feature extraction technique of CNN provided high accuracy on the five classifiers. The KNN was the average best classifier with a 100% accuracy. Experimental results indicated that the PCA improved the classifiers. This study delivers important and significant answers in practice to curb motor vehicle crashes due to drowsiness.","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127963671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-09DOI: 10.1109/ZCICT55726.2022.10045915
Noma Muzunze, Sam Takavarasha
The retail sector is experiencing unprecedented volatility, uncertainty and ambiguity, and these culminated in the closure of some of its notable giants due to the global financial crisis and the novel corona virus pandemic. This paper uses Organisational Mindfulness (OM) and Resource Based View (RBV) to investigate the adoption of data analytics in developing countries using data from Zimbabwe’s retail sector. The results showed that while some industries use big data analytics (BDA), its adoption remains an insurmountable task for some Zimbabwean retailers due to infrastructural, resource and other technical challenges. It revealed that successful adoption of BDA in the retail sector can help change business operations, including the ability to match customer expectations, hone product lines and improve marketing campaigns.
{"title":"Investigating The Challenges of Adopting Data Analytics In Zimbabwe’s Retail Sector","authors":"Noma Muzunze, Sam Takavarasha","doi":"10.1109/ZCICT55726.2022.10045915","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10045915","url":null,"abstract":"The retail sector is experiencing unprecedented volatility, uncertainty and ambiguity, and these culminated in the closure of some of its notable giants due to the global financial crisis and the novel corona virus pandemic. This paper uses Organisational Mindfulness (OM) and Resource Based View (RBV) to investigate the adoption of data analytics in developing countries using data from Zimbabwe’s retail sector. The results showed that while some industries use big data analytics (BDA), its adoption remains an insurmountable task for some Zimbabwean retailers due to infrastructural, resource and other technical challenges. It revealed that successful adoption of BDA in the retail sector can help change business operations, including the ability to match customer expectations, hone product lines and improve marketing campaigns.","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"304 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117306311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-09DOI: 10.1109/ZCICT55726.2022.10045858
Joseph Mutengeni, Alec Musasa, Belinda Mutunhu
Collab is an application that uses distributed computing techniques for effective, real-time collaboration over a Local Area Network (LAN) in either a home, educational, or workplace environment. Users can collaborate by joining a secure collaboration session in the absence of an internet connection. Within a session, users can share messages, digital content, and reviews. Most existing LANbased applications lack important collaboration features. It is against this backdrop that we propose the use of distributed computing techniques in a small-scale, serverless LAN to empower users to collaborate effectively in local teams. Thus, we design and implement a computer application that can be used for collaboration on a LAN in the absence of a centralised web service.
{"title":"Local Area Network Based Collaboration Using Distributed Computing","authors":"Joseph Mutengeni, Alec Musasa, Belinda Mutunhu","doi":"10.1109/ZCICT55726.2022.10045858","DOIUrl":"https://doi.org/10.1109/ZCICT55726.2022.10045858","url":null,"abstract":"Collab is an application that uses distributed computing techniques for effective, real-time collaboration over a Local Area Network (LAN) in either a home, educational, or workplace environment. Users can collaborate by joining a secure collaboration session in the absence of an internet connection. Within a session, users can share messages, digital content, and reviews. Most existing LANbased applications lack important collaboration features. It is against this backdrop that we propose the use of distributed computing techniques in a small-scale, serverless LAN to empower users to collaborate effectively in local teams. Thus, we design and implement a computer application that can be used for collaboration on a LAN in the absence of a centralised web service.","PeriodicalId":125540,"journal":{"name":"2022 1st Zimbabwe Conference of Information and Communication Technologies (ZCICT)","volume":"09 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122916290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：