The recently introduced cashless economy with the cash-lite banking by the Central Bank of Nigeria (CBN) has engineered most Nigeria banks to introduce e-payment and e-transact solutions to support the policy. However, one of the major problems limiting the growth of this new move in Nigeria is the absence of secure and reliable e-payment systems. The problems associated with the implementation of a secure e-payment systems in the country stem from card thefts, internet fraud and identity theft e.t.c, which runs into millions of US dollars annually. This has adversely affected the integrity, development of e-commerce and the country's active participation in the international market. Hence, the need for a secured and reliable mechanism for a proficient implementation of e-payment system in the country. This paper is focused on securing reliable authentication scheme for e-payment system in Nigeria through effective biometric authentication technology.

Colorectal cancer occurs in the rectal of humans, and early detection has been proved to reduce its mortality rate. Colonoscopy is the standard used in detecting the presence of polyps in the rectal, and accurate segmentation of the polyps from colonoscopy images often provides helpful information for early diagnosis and treatment. Although existing deep learning models often achieve high segmentation performance when tested on the same dataset used in model training; still, their performance often degrades when applied to out-of-distribution datasets, leading to low model generalization or overfitting. This challenge is often associated with the quality of the features learnt from the input images. In this work, a novel Context Feature Refinement (CFR) module is proposed to address the challenge of low model generalization and segmentation performance. The CFR module is built to extract contextual information from the incoming feature map by using multiple parallel convolutional layers with progressively increasing kernel sizes. Using multiple parallel convolutions with different kernel sizes helped to extract more efficient multi-scale contextual information and thus enabled the network to effectively identify and segment small and fine details, as well as larger and more complex structures in the input images. Extensive experiments on three public benchmark datasets in CVC-ClinicDB, Kvasir-SEG, and BKAI-NeoPolyp showed that the proposed ConvSegNet model achieved jaccard, dice and F2 scores of 0.8650, 0.9177, and 0.9328 on CVC-ClinicDB, 0.7936, 0.8618, and 0.8855 on Kvasir-SEG, and 0.8045, 0.8747 and 0.8909 on BKAI-NeoPolyp datasets respectively. Also, an improved generalization performance was achieved by the ConvSegNet model, compared to the benchmark polyp segmentation models.

No abstract

No abstract

The introduction of the Automated Teller Machine (ATM) by financial institutions has changed the face of banking globally, Nigeria inclusive. The mechanism has provided a kind of collective sigh-of-relief to both the bank and their customers, offering convenient, speedy and round the clock services. However, it is not without some inherent challenges as many bank customers who are not proficient in English language found the ATM cumbersome and unfriendly. Attempting to provide solution to these challenges, some banks in Nigeria have developed and introduced the indigenous language version of the Automated Teller Machine options. Yet, user’s response did not reflect the anticipated level of enthusiasm as a result of operational complexities and translation equivalence challenges especially for the Yoruba menu option. In view of this, this work makes an attempt to present an improved translation model introducing Yoruba tone marking to assist those who do not understand the English language, but are monolingual only in Yoruba language to effectively interact with the system. Specifically, an attempt is made to translate the menu option of Automated Teller Machine in conformity with the phonological and morphological processes in Yorùbá, following the natural strategy of lexical expansion in the Yorùbá language itself. Phrases and sentences of translation were conducted, employing equivalent model. The data (content) considered were arranged bearing in mind the principle of relatedness for proper reference and analysis. During translation, the strategies of morphological processes of semantic extension, borrowing, nominalization, indigenization and composition were used. The system framework designed to test the model was found to reflect the anticipated level of user’s enthusiasm. The research work does not only assist those who are not proficient in English language to effectively interact with the system, but also overcomes the challenges of the present design and consequently widens the scope of ATM usage in the interior parts of the country.