No abstract

Learning rates in gradient descent algorithms have significant effects especially on the accuracy of a Capsule Neural Network (CNN). Choosing an appropriate learning rate is still an issue to date. Many developers still have a problem in selecting a learning rate for CNN leading to low accuracies in classification. This gap motivated this study to assess the effect of learning rate on the accuracy of a developed (CNN). There are no predefined learning rates in CNN and therefore it is hard for researchers to know what learning rate will give good results. This work, therefore, focused on assessing the effect of learning rate on the accuracy of a CNN by using different learning rates and observing the best performance. The contribution of this work is to give an appropriate learning rate for CNNs to improve accuracy during classification. This work has assessed the effect of different learning rates and came up with the most appropriate learning rate for CNN plant leaf disease classification. Part of the images used in this work was from the PlantVillage dataset while others were from the Nepal database. The images were pre-processed then subjected to the original CNN model for classification. When the learning rate was 0.0001, the best performance was 99.4% on testing and 100% on training. When the learning rate was 0.00001, the highest performance was 97% on testing and 99.9% on training. The lowest performance observed was 81% accuracy on testing and 99% on training when the learning rate was 0.001. This work observed that CNN was able to achieve the highest accuracy with a learning rate of 0.0001. The best Convolutional Neural Network accuracy observed was 98% on testing and 100% on training when the learning rate was 0.0001.

Egg storage has been a problem due to ineffective methods subjecting many farmers and egg retailers to losses. These techniques include various models involving statistical analysis of the storage conditions on the egg quality. Apparent deficiencies of the information from the randomized complete block design model prompted this study. The study evaluated the effect of storage temperature at three levels (5 ° C , 19.5 ° C , 30 ° C ) and duration at four levels (2 nd , 12 th , 22 nd , 32 nd ) on egg quality using a fixed and mixed-effect model. We used a total of 618 fresh and unfertilized eggs from ISA (Institut de Sélection Animale) brown layers. We determined egg quality by the changes of physical characterization under storage conditions. The study used Restricted maximum likelihood and analysis of variance methods to assess the efficiency of fixed and mixed effect models. Results showed that the physical components of the egg were significantly affected at 5 ° C , 19.5 ° C , and 30 ° C . The effect was more adverse on eggs stored at 30 ° C for 32 days. However, storage temperatures of 5 ° C and 19.5 ° C led to an extensive reduction in the Haugh unit, yolk index, and egg white height. On the other hand, it increased the weight loss and albumen diameter under storage for 2 nd , 12 th , 22 nd and 32 nd -time intervals. Based on these findings, the study recommends 5 ° C for egg quality preservation. The eggs should be refrigerated for 32 days, stored at 19.5 ° C for 14 days, and lastly kept at 30 ° C for a maximum of 7 days. The fixed-effect models exhibited more minor variances in diameter and height of albumen, yolk index, weight loss, and Haugh unit. This overlapped instances where the fixed-effect models were significantly the same as the mixed-effect models. This study proposes that the fixed effect model is the most appropriate for randomized completely block design experiments.

The ubiquitous nature of mobile technologies and devices, present new challenges and opportunities for Deposit-Taking Savings and Credit Cooperative Societies (SACCOs) as they integrate them into their processes with the hope of improving their performance. To enhance their performance, Deposit-Taking SACCOs have adopted and are using mobile communication services including mobile messaging, mobile call services, mobile email, mobile chatting and mobile conferencing services. However, the effect of these mobile communication services on performance of Deposit-Taking SACCOs has not been well studied. Even though some studies have indicated the positive potential of mobile communication services, other studies indicate that they have no effect on organizational performance. Given these contradictions, this study sought to investigate the effect of mobile communication services on performance of Deposit-Taking SACCOs in Kenya. Descriptive and explanatory research designs were adopted using quantitative and qualitative approach to data collection, analysis and reporting. The study used a sample of 86 Deposit-Taking SACCOs drawn from a target population of 110 Deposit-Taking SACCOs that were licensed by SACCO Societies Regulatory Authority as at 31st December 2011. A structured questionnaire administered to two managers (from information technology and finance departments) in each SACCO was used to collect primary data. Inferential analysis revealed the exististence of statistically significant positive effect of mobile communication services on performance of Deposit-Taking SACCOs in Kenya. The study therefore recommends investments and increased utilization of mobile communication services within DepositTaking SACCOs in Kenya.

Deposit-Taking Savings and Credit Cooperative Societies have embraced mobile banking services to address efficiency challenges characterized by poor information delivery channels and high operational costs and to enhance their financial performance. However, the effect of mobile banking services on the performance of Deposit-Taking Savings and Credit Cooperative Societies has not been well studied. Even though some studies have indicated the potential of mobile banking services towards improving organizational performance, other studies have indicated otherwise. Given this contradiction, this study sought to investigate the effect of mobile banking services on the performance of Deposit-Taking Savings and Credit Cooperative Societies in Kenya. Descriptive and explanatory research designs were adopted. Using simple random sampling, the study was based on a sample of 86 Deposit-Taking Savings and Credit Cooperative Societies drawn from a target population of 110 Deposit-Taking Savings and Credit Cooperative Societies that were licensed by SACCO Societies Regulatory Authority as at 31st December 2011. The study found that three mobile banking services including mobile deposits services, mobile bill payments services and mobile statements services had a positive statistically significant effect on the financial performance of Deposit-Taking SACCOs in Kenya and therefore recommends their utilization to enhance the financial performance of the SACCO subsector.