Sort by
Secure Content Based Image Retrieval System Using Deep Learning

This paper investigates Content-Based Image Retrieval (CBIR) using an ensemble of three cutting-edge deep learning architectures: Xception, MobileNet, and Inception. This ensemble approach demonstrated exceptional retrieval accuracy, with Xception and Inception models achieving an accuracy of 92.375%, precision and recall of 93% and 92% respectively, and an F1-score of 92%. The MobileNet model also showed strong performance, with an accuracy of 87.125%, precision and recall of 88% and 87%, and an F1-score of 87%.Beyond mere retrieval accuracy, the study places a significant emphasis on the security of the image database. A dual-layer encryption method was employed, integrating visual cryptography with the Advanced Encryption Standard (AES) to ensure robust protection of sensitive data. This approach guarantees efficient image retrieval based on content while securing the data against potential breaches.The results underscore the efficiency of the ensemble model in balancing high retrieval accuracy with stringent security measures. This balance is particularly relevant for applications in digital libraries, historical research, fingerprint identification, and crime prevention. The paper’s findings advocate for the critical need to integrate strong security protocols in future CBIR systems, ensuring optimal performance without compromising data security.

Open Access
Relevant
The Role of Agricultural Projects in Building Sustainable and Resilient Maize Value Chain in Burkina Faso

Poor seed quality and climate change significantly affect the maize value chain in Burkina Faso. To address the challenges, a catalytic project titled “Strengthening resilient seed systems in the maize value chain in Burkina Faso—from research to markets” was initiated to enhance the development of a resilient maize value chain. This study aims to assess the role of the project in developing a sustainable and resilient maize value chain. In this study, we used a mixed approach in design and implementation: qualitative research using key informants’ interviews, secondary data such as baseline survey reports, and lessons learned during the seed value chain greening intervention implemented in the Hauts-Bassins and Cascades regions of Burkina Faso. We analyzed qualitative data following the Gioia method. Kabako, a drought-tolerant hybrid seed variety, doubled crop yields in demonstration plots compared to smallholder farms and regional and national averages. Extension officers and village-based advisors (VBAs) were trained on improved seeds, composting, strip cropping, intercropping, crop rotation, and water management technologies and afterward trained smallholders. The VBAs trained smallholders on proper postharvest management practices and processing. The off-takers acted as the market. However, smallholders also sold their maize products in the informal open markets. The aggregator system was the missing link in Burkina Faso’s maize value chain. There was limited involvement of women in the project. Results obtained from this study are valuable for policymakers and value chain actors in preparing policies and filling missing gaps for exploiting the potential of the maize value chain.

Open Access
Relevant
Selected conservation management strategies enhance maize yield stability in the sub-humid tropical agro-ecozone of Upper Eastern Kenya

Conservation management strategies have been recommended to enhance soil fertility, moisture retention, crop yield, and yield stability in rainfed agriculture. However, there is limited research on yield stability. We evaluated the effect of integrating soil inputs in conservation tillage on yield and yield stability in Meru South, Upper Eastern Kenya, for eleven consecutive cropping seasons. The trial treatments included conservation tillage without soil inputs (Mt), conservation tillage with soil inputs: sole inorganic fertilizer (F), residue + inorganic fertilizer (RF), residue + inorganic fertilizer + manure (RFM), residue + manure + legume Dolichos Lablab L. (RML), residue + Tithonia + manure (RTM), residue + Tithonia + phosphate rock (RTP) and conventional tillage (Control). Conservation tillage with RFM was the best-fit strategy for enhancing yields. There was heterogeneity in yield residual variance. A larger residual variance implied lesser yield stability. Mt treatment had the least yield residual variance of 0.12 Mg ha−2, followed by Ct and RML, 0.15 Mg ha−2, while RTM had the highest yield residual variance of 0.62 Mg ha−2. Contrarily, the most stable treatments had the least average yields. The study indicated a positive influence of incorporating soil inputs in conservation tillage on yield and suggests longer-term research for yield stability.

Open Access
Relevant