Unrepaired deoxyribonucleic acid in skin cells causes skin cancer by generating genetic abnormalities or mutations, rising day by day. Detecting or diagnosing skin cancer in its initial stages is expensive and challenging, giving superior treatment options. Given the severity of these issues, researchers have generated a set of early classification techniques for skin cancer. Skin cancer is diagnosed and segregated from melanoma by looking at the symmetry, color, size, shape, and other features of lesions. While there are various computerized approaches for classifying skin lesions, convolutional neural networks (CNNs) have exceeded standard practices. In this paper, we have used multiple machine learning libraries. Also, we have used five pre-trained models such as VGG-16, VGG-19, Inception V3, Efficient Net B7, ResNet 50 models and presented our proposed model for skin cancer classification using the HAM10000 dataset, which is an enormous skin cancer dataset. This research reports a maximum accuracy of 85.25% for Inception V3 models within five pre-trained models and the highest accuracy of 90.55% for our proposed model. In terms of image detection, our experimental settings show that our suggested model achieved the best classification accuracy than the other five pre-trained models. Our findings are helpful in providing a comprehensive comparison with brief analysis of many deep neural networks in the categorization of skin cancer.

Maize (Bhutta) is one of the important growing cereal crops in Bangladesh. Toxigenic fungi such as Aspergillus and Fusarium infect stored maize grains. Enzyme-linked immusorbent assay (ELISA) was used to determine total aflatoxins and fumonisins contamination in stored maize grains collected from 15 Bangladeshi maize-producing areas. The highest total concentration of aflatoxins (103.07 µg/kg) and fumonisin (9.18 mg/kg) was found in Chuadanga and Gaibandha, whereas the lowest was detected for aflatoxins (1.07 µg/kg) and (0.11 mg/kg) in Dinajpur and Cumilla, respectively. The findings clearly demonstrated that aflatoxin concentrations in samples from six regions and fumonisin concentrations in samples from 10 regions were beyond the regulatory limit of aflatoxin (10 ppb) and fumonisin (1 ppm), respectively, as set by European Union (EU). However, a positive correlation between aflatoxins with toxigenic A. flavus, and fumonisins with toxigenic Fusarium spp. was observed. The fungi associated with maize grains were identified by sequencing of ITS regions. Moreover, toxigenic A. flavus was confirmed using primers specific to nor, apa2, omtA and primer FUM1 for F. proliferatum and F. oxysporum. Since the Bangladesh Food Safety Authority has not authorized any precise regulation limits for maize mycotoxin contamination, these results will serve as a benchmark for monitoring mycotoxin contamination in maize and also to develop globally practiced biocontrol approach for producing safe food and feed.