BlueCrest University College

Cervical cancer is a critical imperilment to a female's health due to its malignancy and fatality rate. The disease can be thoroughly cured by locating and treating the infected tissues in the preliminary phase. The traditional practice for screening cervical cancer is the examination of cervix tissues using the Papanicolaou (Pap) test. Manual inspection of pap smears involves false-negative outcomes due to human error even in the presence of the infected sample. Automated computer vision diagnosis revamps this obstacle and plays a substantial role in screening abnormal tissues affected due to cervical cancer. Here, in this paper, we propose a hybrid deep feature concatenated network (HDFCN) following two-step data augmentation to detect cervical cancer for binary and multiclass classification on the Pap smear images. This network carries out the classification of malignant samples for whole slide images (WSI) of the openly accessible SIPaKMeD database by utilizing the concatenation of features extracted from the fine-tuning of the deep learning (DL) models, namely, VGG-16, ResNet-152, and DenseNet-169, pretrained on the ImageNet dataset. The performance outcomes of the proposed model are compared with the individual performances of the aforementioned DL networks using transfer learning (TL). Our proposed model achieved an accuracy of 97.45% and 99.29% for 5-class and 2-class classifications, respectively. Additionally, the experiment is performed to classify liquid-based cytology (LBC) WSI data containing pap smear images.

Abstract Purpose: The main purpose of this quantitative research was to assess various e-business strategies implored by small and medium enterprises (SMEs) in Ghana during the Covid-19 pandemic. Research methodology: It made use of a descriptive design. Data was collected with the use of a structured questionnaire, analysed with excel and presented in tables and figures. Results: The study revealed that small business owners have knowledge of e-business models with the most popular e-business model used being the Business to Consumer (B2C) model, while the least used model was the Business to Government (B2G) model. While imploring the use of e-business models and strategies, SMEs were faced with the challenge of very limited knowledge on the use of e-business strategies. Limitations: The study was limited to businesses in the Tema Metropolitan Assembly of Ghana. Contribution: Most of the SMEs were established in the traditional setting of business operations therefore there was little or no plan for integrating the internet in their operations. However, the pandemic has shifted their attention to adopting some virtual traction to their businesses for the benefit it offers such as continuous sales and more visibility. Further research on how each of the various concepts was used by SMEs is highly recommended.

The feelings of WEB users have a great influence on rest of the users, product sellers and market analysis. It is necessary to well structure the unstructured data from various social platforms for proper and meaningful analyses. For the classification of multilingual data, the analysis of feelings has recognized significant attention. This is called textual organization that may be used to classify state of mind or feelings expressed in different ways like: negative, positive, favorable, unfavorable, thumbs up, thumbs down, etc. in the field of Automatic Language Processing (NLP). To solve this kind of problem, sentiment analysis and deep learning techniques are two merging techniques. Because of machine learning ability, deep learning models are effectively used for this purpose. Recurrent Neural Networks (RNN) and Naive Bayes algorithm are two popular deep learning architectures to analyze feelings in sentences. These architectures may be used in natural language processing. In this research article, we propose solutions to multilingual sentiment analysis problem by implementing algorithms and in order to contract the result, we compare precision factor to find the best solution for multilingual sentimental analysis.

The surge in artisanal gold mining (AGM) activities and the associated environmental impact in Ghana have elicited several stakeholders' attempts to curb the problem. However, due to little understanding of the underlying issues, these efforts have been ineffective. This study aims to use a socio-ecological framework to analyze drivers of AGM activities, the environmental pressures, the state change, their impact on human welfare, and the management response as measures (DAPSI(W)R(M)) to the problem. Evaluate AGM's impact on Ghana's ability to achieve the United Nations Sustainable Development Goals (SDGs). Data were collected from relevant literature on the subject and analyzed with the DAPSI(W) R(M) framework. Esteem needs, food, acceptance and friendship, and self-actualization are the main drivers of AGM activities leading to environmental pressures, including abrasion, extraction of living and non-living resources, the introduction of non-synthetic compounds, among others. State changes of the environment resulting from the pressures generated by human activities were changes in the land and forest cover (1.13%), topography (hills turned into flatland and undulating), and biota. Due to the state in the environment, water quality and availability, agriculture food production, fish yield, food safety, spiritual and cultural loss, death, injury, and health of gold miners and other stakeholders have been affected.

The purpose of the study was to investigate the effects of service quality and customer satisfaction on customers’ loyalty in the hospitality industry in Cape Coast, Ghana. Descriptive design was used to investigate the association between service quality, customer satisfaction, service quality and customer satisfaction (independent variables) and customers’ loyalty (dependent variable). Survey was used for data collection from 320 customers in the hospitality industry in Cape Coast, Ghana. Data analysis was carried out with the use of SPSS version 20. The findings showed a significant positive relationship between service quality and customers’ loyalty in the hospitality industry in Cape Coast, Ghana. The study also found a significant positive relationship between customer satisfaction and customers’ loyalty in the hospitality industry in Cape Coast, Ghana. It was recommended that the firms in the hospitality industry in Cape Coast, Ghana, should strive to continue the delivery of quality service to ensure loyalty. This can be done by maintaining consistent quality service performance. Also, it was recommended that the firms in the hospitality industry in Cape Coast, Ghana, should continue to endeavour to meet customers’ expectation since it engenders loyalty. Periodic market research is imperative to help identify emerging needs of customers so as to enhance the loyalty.

Today's world is a global village. Everyone is connected to one another in this vast network generated by the Internet. As social media sites continue to grow in popularity it promises a lot for the modern youth. Social media has been widely adopted, with high enthusiasm among youth around the world. With very few studies focusing on youth social media use in Ghana there is wide open array of work to be done. Based on the findings of several research studies in social media area, it has been found that these Social networking sites are having a great impact on the lives of young people. Also since most of the research works have been carried out in other countries, it was found necessary and important to carry out a study in Ghana on the impact of Social Media on the youth. The main objectives of this study were to investigate the extent of social media use and the purposes, access and impact of its use by the young people in Ghana. Two hundred youth aged between 15-25 participated in the study. The findings revealed patterns of young people's social media use consistent with similar studies of youths in other countries. The study revealed the need for young people to have a greater awareness of the risks of social media use. It was found that the majority of Ghanaian youths were using Social media on an enormous scale, mainly for communication purposes. According to this study, although social media has a positive impact on the youth, yet quite a large number of respondents reported having met with negative experiences on these online sites.

Pathogens, including viruses, bacteria, and fungus, are the biotic agents that cause illnesses in crops and are the major cause of yield losses of up to 16 percent in certain parts of the globe. Pathogens are the primary cause of yield losses in some parts of the world. Deep learning algorithms, which are at the cutting edge of technology, are now being used to identify crop disease at an earlier stage. Supervised learning (support vector machine and K‐nearest neighbor), ensemble learning (random forest and AdaBoost), and deep learning approaches were used in this study to suggest a classification of paddy leaf diseases, including bacteria leaf blight, blast, hispa, leaf spot, and leaf folder (neural networks). In order to evaluate the performance of the learning approaches, accuracy, recall, precision, F 1 score, and area under the receiver operating characteristic curve were used to evaluate the performance of the interpretation (ROC and AUC). According to the results of the investigation, when the fold value grows, the value of the evaluation metrics (AUC, CA, F 1, precision, and recall) increases in a progressive manner, i.e., the 0.001 value increases as compared to the values obtained with the previous folds. When comparing the neural network to the baseline classifiers, the assessment metrics demonstrate that the neural network performs much better.

This study (a) examined the daily composition of 24‐hr movement behaviors in children with ASD using objective measures, and (b) applied compositional analysis to examine the associations of the time spent in moderate‐vigorous physical activity (MVPA), light physical activity (LPA), sedentary behavior (SB), and sleep duration (SD) with body mass index (BMI), relative to the time spent in the other movement behaviors in a sample of children (aged 7–19 years) with ASD. Time spent in MVPA, LPA, SB, and SD were measured using accelerometers over a 7‐day period. BMI was calculated from measured height and weight. Participants ( n = 46) spent 40% of time in LPA ( M = 9.6 hr), 30.6% ( M = 7.34 hr) in SB, 24.9% ( M = 5.98 hr) asleep, and 4.5% ( M = 64.8 min) in MVPA. Reallocating 30 min from LPA to SD decreased BMI by 0.471 kg/m 2 ( P = 0.003). Reallocating 30 min from MVPA to SD decreased BMI by 0.658 kg/m 2 ( P = 0.051). Reallocation of 60 min in equal proportions from SB, MVPA, and SD to LPA increased BMI by 0.418 kg/m 2 ( P = 0.021), and reallocation of 60 min in equal proportions from LPA, MVPA, and SD to SB increased BMI by 0.295 kg/m 2 ( P = 0.052). Finally, reallocation of 60 min in equal proportions from SB, LPA, and MVPA to SD decreased BMI by −0.845 kg/m 2 ( P = 0.001). Lay Summary Data was collected on time spent in light physical activity (LPA), moderate‐vigorous physical activity (MVPA), sedentary behavior (SB), and sleep in 46 children with autism. The sample had insufficient sleep (a mean of 6 hr/night). We showed that replacing 30 min of LPA or MVPA with sleep decreased BMI. Also, moving 60 min to LPA or SB from the remaining movement behaviors (i.e., 20 min from each) increased BMI, and moving 60 min to sleep from the remaining behaviors decreased BMI.

The hybrid wireless sensor network is made up of Wireless Body Area Network (WBAN). Generally, many hospitals use cellular networks to support telemedicine. To provide the treatment to the patient on time, for this, an early diagnosis is required, for treatment. With the help of WBANs, collections and transmissions of essential biomedical data to monitor human health becomes easy. Compressor Sensing (CS) is an emerging signal compression/acquisition methodology that offers a protruding alternative to traditional signal acquisition. The proposed mechanism reduces message exchange overhead and enhances trust value estimation via response time and computational resources. It reduces cost and makes the system affordable to the patient. According to the results, the proposed scheme in terms of Compression Ratio (CR) is 18.18% to 88.11% better as compared to existing schemes. Also in terms of Percentage Root-Mean-Squared Difference (PRD) value, the proposed scheme is 18.18% to 34.21% better than with respect to existing schemes. The consensus for any new block is achieved in 24% less time than the Proof-of-Work (PoW) approach. The shallow CPU usage is required for the leader election mechanism. CPU utilization while the experiment lies in the range of 0.9% and 14%. While simulating a one-hour duration, the peak CPU utilization is 21%.

Adoption of technology and Higher Education are two major driving forces, especially for emerging economies. Cloud computing is one such technology which is not only transforming enterprise businesses but also higher education. Adoption of cloud computing in the primary, higher and research-oriented education is playing an important role as far as ease of functionality, user support, cybersecurity, on-demand scaling, time-saving, and costing are the concern. Education institutions should be encouraged and mentored very well for the adoption of the technology-based teaching and learning to improve and overcome their operational and academic challenges, which will be a win-win situation for all stakeholders i.e. Educational Institutions, Government, Technology Companies. This research article introduces a conceptual framework for the adoption of Hybrid EduCloud in higher education. This study is based on Ethiopia, one of the SubSaharan African country. The qualitative research methodology was adopted to formulate Hybrid EduCloud model and the fivestep conceptual framework of cloud computing implementation strategies for higher education while quantitative research methodology was used for questionnaire survey in connection with five steps of cloud computing implementation strategy model. The result shows that this model can be an important contribution to boost cloud-computing adoption in higher education.

Although job stress has become an issue of great concern over the last decades both internationally and nationally, there still remains a paucity of research in the Ghanaian insurance industry. This study therefore examined the relationship between antecedent variables (work overload, role conflict and role ambiguity) and employee job stress in the insurance industry in Ghana. Using a descriptive cross-sectional design with a survey questionnaire, 212 employees were selected to participate in the study. Pearson correlation and a two-step hierarchical regression were used to test the proposed hypotheses. Results of the analysis revealed that work overload and role conflict rather than role ambiguity were positively related to job stress. Implications for theory and practice are later discussed in the study.

Python libraries are used in this chapter to create data science models. Data science is the construction of models that can predict and act on data, which is a subset of machine learning. Data science is an essential component of a number of fields because of the exponential growth of data. Python is a popular programming language for implementing machine learning models. The chapter discusses machine learning's role in data science, Python's role in this field, as well as how Python can be utilized. A breast cancer dataset is used as a data source for building machine learning models using Python libraries. Pandas, numpy, matplotlib, seaborn, scikit-learn, and tensorflow are some Python libraries discussed in this chapter, in addition to data preprocessing methods. A number of machine learning models for breast cancer treatment are discussed using this dataset and Python libraries. A discussion of machine learning's future in data science is provided at the conclusion of the chapter. Python libraries for machine learning are very useful for data scientists and researchers in general.

Artificial Intelligence is a transformative technology with the potential to both displace and create jobs across industries. Experts believe it will greatly benefit humanity by reducing tedious tasks and advancing technology. The World Economic Forum predicts that by 2025, 50% of tasks will be automated, compared to the current 29%, and around 75% of companies plan to adopt AI, with 50% expecting it to drive job growth, according to their 2023 report. Fast-growing roles stem from technology, digitalization, and sustainability. By 2025, AI will replace 75 million jobs but generate 133 million new ones, resulting in a net increase of 58 million jobs globally. However, certain industries will face significant displacement, and AI's impact on unemployment rates will differ across countries, regions, and industries. AI will likely displace jobs in manufacturing but boost employment in healthcare and education. However, experts warn of AI's risks for job market in Africa, citing automation replacing repetitive tasks like data entry and customer service. Adapting skills to the changing job landscape is crucial, but it comes with added costs for both individuals and organizations. AI advancements are set to automate routine jobs, potentially causing employment shifts in Africa, similar to global trends. New opportunities in AI, data science, and tech may emerge, but the impact hinges on AI adoption speed, infrastructure, and policies. Challenges like skills gaps, data ecosystems, ethics, policies, infrastructure, and user attitudes hinder AI adoption, affecting industries, as seen in Ghana. To boost AI adoption in Africa, building strong ecosystems involving policymakers, universities, companies, startups, and partnerships is crucial. Failure to address these challenges will hinder Ghana and Africa's progress, causing them to fall behind globally. This paper highlights the hurdles faced by Ghana and African nations in AI adoption, emphasizing job displacement and unemployment effects on job seekers. Its aim is to equip policymakers and stakeholders with insights into AI's disruptive nature, aiding in the creation of sustainable policies for the industry. The study started with a review of AI disruption's impact on future jobs in Africa using secondary sources on evolving AI tech. It also involved gathering firsthand data via interviews in Ghana to understand challenges in AI adoption, especially among industry professionals.

Governments need accurate tax revenue forecast figures for good economic planning but there seems to be no consensus on which method is the most suitable to deliver reliable results leading to differences in the choice of technique from one country to another. This study therefore forecasts Ghana’s Value Added Tax (VAT) Revenue by comparing two methods, ARIMA with Intervention and Holt linear trend methods to establish the one with more precise predictive powers for VAT Revenue. Monthly VAT revenue data from the year 2002 to 2019 is used in the analysis. The findings show that ARIMA with Intervention method outperformed the Holt linear trend model in terms of accuracy and precision. A comparison of predicted results from the ARIMA with intervention model from 2017 to 2019 with Ghana Revenue Authority’s VAT revenue targets based on their in-house forecasting model for the same period reveals that the ARIMA with intervention approach performs better than the in-house forecasting model of the VAT authority. In this case, the study recommends the ARIMA with intervention method to the tax authority for consideration in its forecasting.

Mobile Cloud Computing (MCC) is an emerging research topic in the world of Information Technology, this trend promises to deliver and promote a wide range of advantage to it anxious markets or clients. With MCC, all the applications that exist are on a remote server enable the individual client machines or devices to access them. Mobile Cloud Computing in smartphone and tablets allows devices to offload functions and data resources to a cloud environment. This happening conserve the power of the smart devices or the tablets to prolong it battery longevity. This book sought to analyses how MCC affect individuals on smart devices as well as their views on network data. The growing demand for mobile devices and its applications are evident that MCC is the next IT trend. The book will also seek the views of people on the cost of applications and battery life of the smart devices as this directly influence the time they spend on their devices. This book would be useful for research scholars as a text for university undergraduate courses related to mobile cloud computing, as well as at junior colleges, and vocational schools training course.

Abstract: Purpose: This study aimed at examining how recruitment and selection practices influence organisational strategic goals. Research methodology: A descriptive case study design was employed. Data was collected from 311 employees of Nestle Water Company who were randomly selected. Results: The study showed that screening affects profitability and market share positively though the effects were insignificant. The selection test on the other hand affects profitability both positively and significantly. There was however a positive insignificant relationship between the selection test and market share. Lastly, the study showed that there exists a positive significant relationship between e-recruitment and profitability; as well as e-recruitment and market share of Nestle water company. Limitations: This study focused on just four recruitment and selection tools as well as employees of Nestle water company. Contribution: The general assertion of scholars that screening, selection tests, e-recruitment, and employee referral have the capacity to stimulate an increase in the profitability and market share of an organisation was confirmed. It is recommended that future studies consider other recruitment and selection tools which were not considered in this study. Keywords: 1. Recruitment 2. Selection 3. Practices 4. Strategic 5. Goals

Purpose: The primary goal of the research was to assess the relationship between Ghanaian commercial banks' profitability and portfolio management. Research methodology: All nine of the Ghana Stock Exchange (GSE)'s listed banks were included in the population of this descriptive study. All nine banks were sampled. This study only considered data from financial statements and bank reports covering the five-year period between 2016 and 2021. Results: Results showed that asset investment has a positive effect on the financial performance of commercial banks in Ghana. Additionally, a positive effect of the loan portfolio on the commercial banks’ financial performance was found. It was finally discovered that asset investment affects the banks’ financial performance in a significantly positive way. Limitations: The study was limited to nine banks listed on the GSE. Contribution: It was concluded that when there is a good loan portfolio management policy, banks perform well and are profitable. Consequently, it is advised that top management and other stakeholders play a crucial role in achieving strategic goals by championing best practices in portfolio management and evaluating the sufficiency of effective portfolio management factors in an unbiased manner.

With the advent of internet, there is a complete paradigm shift in the manner we comprehend computing. Need to enable ubiquity, convenient and on-demand access to resources in highly scalable and resilient environments that can be remotely accessed, gave birth to the concept of Cloud computing. The acceptance is so rapid that the notion influences sophisticated innovations in academia, industry and research world-wide and hereby change the landscape of information technology as we thought of. Through this book, the authors tried to incorporate core principles and basic notion of cloud computing in a step-by-step manner and tried to emphasize on key concepts for clear and thorough insight into the subject. This book begins with the fundamentals of cloud computing, its service and deployment models, architecture, as well as applications and platforms. It presents some key enterprise strategies and models for the adoption of and migration to cloud. Privacy and security issues and challenges also form a major part of our discussion in the book as well as case studies of cloud computing adoption in Sub-Saharan Africa and India. The book concludes with a discussion of several advanced topics, such as Amazon Web Services (AWS), Open Nebulla, Microsoft Azure, Apache Hadoop and Google App Engine (GAE).

Purpose: The study examined the role of e-leadership in adapting to technological development. Research methodology: A mixed methods triangulation approach was used for the study. Quantitative data was collected from 297 customers and 146 employees of telecommunication companies in Ghana using a questionnaire. For qualitative data, 12 respondents were interviewed. Quantitative data were analyzed with descriptive statistics for IBM SPSS Statistics 24. Qualitative data were analyzed using content analysis. Results: It was found that e-leadership discourages face-to-face interactions. Leaders tend to employ the use of social media when communicating with team members during rapid technological development. Virtual teams are employed while completing projects. Managers show empathy, provide effective supervision and are always available online to assist virtual team members who happen to encounter challenges, in a timely manner. Limitations: This study was limited to employees and customers of telecommunication companies in Ghana. Contribution: This research has exposed that E-leadership positively affects the productivity of virtual team members, who tend to face challenges during technological advancement. This implies that with e-leadership, the level of difficulty faced while adapting to rapid technological development is significantly reduced. Novelty: There is a need for managers to be consistent with the application of the e-leadership concept no matter how sophisticated technology gets. It is therefore recommended that managers continue with the use of e-leadership while providing guidance for challenged virtual team members.

This descriptive research study has been undertaken in Tirunelveli city, Tamilnadu to foresee and differentiate perception of the nurses working in multi-speciality and single speciality hospitals towards the impact of employee turnover on performance of existing nurses. The study has sampled 120 nurses (60 from multi and 60 from single speciality hospitals) qualified with Diploma in General Nursing and Midwifery (DGNM) and Bachelor in Nursing (B.Sc Nursing) courses using judgement sampling technique. The analysed primary data collected through a constructed questionnaire has found that nurses working in single speciality hospitals have shown higher perception towards work load, work time, loss of interest, work stress and inability to provide information than multi-speciality hospitals. Nurses working in both kinds of hospitals have shown equal perception towards health related problems, conflict and dispute, sense of commitment and morale. Nurses who are working in both kinds of hospitals with the characteristic of married, less than 30years of age, drawing less than Rs.8000 salary and having less than 2years of work experience have shown high perception towards impact of employee turnover on performance of existing nurses.