To combat the problem caused by the Fall Army Worm in the country there is a need to come up with robust early warning and monitoring systems as the current manual system is labor intensive and time consuming. The automation of the identification and classification of the insect is one of the novel methods that can be undertaken. Therefore this paper presents the results of training a Convolutional Neural Network model using Google’s Tensorflow Deep Learning Framework for the identification and classification of the Fall Army worm moth. Due to lack of enough training dataset and good computing power, we used transfer learning, which is the process of reusing a model trained on one task as a starting point for a model on a second task. Googles pre-trained InceptionV3 model was used as the underlying model. Data was collected from four sources namely the field, Lab setup, by crawling the internet and using Data Augmentation. We Present results of the best three trials in terms of training accuracy after several attempts to get the best metrics in terms of learning rate and training steps. The best model gave a prediction average accuracy of 82% and a 32% average prediction accuracy on false positives. The results shows that it is possible to automate the identification and classification of the Fall Army worm Moth using Convolutional Neural Networks.

Zambia’s agricultural sector through Food Reserve Agency (FRA) while still underdeveloped faces many challenges that range from marketing, spoilage, infestations, and theft at site, spillage and storage among others. The methods used by FRA in their business processes are largely manual as there are no systems in place. In order to help curb these problems, this paper proposed and developed novel methods that can be used to sense real-time warehouse intrusion and grain tracking within the FRA circulation. The IoT based prototype model made use of the APC220 transceiver, GSM, GPRS, RFID, PIR and cloud storage. To curb theft of grain at storage points, the system used motion sensing through the use of PIR sensors, wireless radio communication module and the GSM/GPRS technologies such that when anyone comes in the range of PIR sensor, then the sensor will send a logic signal to the microcontroller. Lastly, the RFID combined with GSM and Arduino microcontroller responsible for grain tracking. From the results obtained in the experiment conducted it is believed that once this technology is adopted, theft will be reduced and grain management in the FRA satellite Depots dotted around the country will improve.

Inventory management of spares is one of the activities Zambia Air Force (ZAF) undertakes to ensure optimal serviceability state of equipment to effectively achieve its roles. This obligation could only be made possible by automating the current manual and paper based inventory system. A web based inventory management system using cloud architecture and barcode technology was proposed. A literature review was conducted on three technologies used in the inventory management that is Radio Frequency Identification (RFID), Barcode Technology and Near Field Communication (NFC). A review was also undertaken on the related works to identify the concept that could be adopted in the proposed system. A baseline study was performed to understand the challenges faced by ZAF in the inventory management of spares. The results of the baseline study were analyzed and found that the challenges were attributed to the current manual inventory management system mainly due to human errors, incorrect inventory reporting and pilferage of items. The proposed prototype system was developed and tested and proved to be faster, efficient and more reliable than the manual and paper based system.

The recent years have seen a rise in the number of cases of cyber-crime committed through identity theft and fraud. To address this problem, this paper uses adaptive neural-fuzzy inference system, fuzzy logic and artificial neural network to implement a multifactor authentication system through a technique of information fusion. To begin with, the identity attributes are mined using the three corpora from three major sources namely the social networks, a set of questionnaires and application forms from the various services offered both in the real and cyberspace. The statistical information generated by the corpora is then used to compose an identity attribute metric model. The composed identity attributes metrics values classified as biometrics, device metrics and pseudo metrics are then fused at the score level through a technique of information fusion in a multifactor authentication system by using each of the above artificial intelligence technologies and the results compared.

The increase in the number of users accessing online services using communication devices such as computers, mobile phone and cards such credit cards has prompted most governments and business organizations to change the way they do business and manage their identity information. However Internet users are vulnerable to identity fraud, which is on the increase and costing the global industry excessive amounts. In this paper we propose Digital Identity Management System (DIMS) as a solution for managing digital identity information. The system proposed uses technologies like artificial intelligence and biometrics on the current unsecured networks to maintain the security and privacy of users and service providers in a transparent, reliable and efficient way. DIMS in this paper will use Multimodal Authentication (MA). MA will be implemented using a technique of information fusion with artificial neural networks to combine the user credentials for optimum recognition of a user. Keywords Credentials, Attributes, Digital Identity, Authentication, Authorization, Information Fusion

This study investigated the complex relationship between technology adoption and the overall performance of selected Zambian banks. The analysis focuses on four prominent banks in Lusaka, namely Zanaco, Atlasmara, Stanbic, and FNB, which were selected based on characteristics such as footprint and income. The time frame is from 2015 to 2020, allowing for a complete examination of trends in the ever-changing banking business. The study used a mixed-methods approach, combining quantitative financial data analysis with qualitative analysis. Data was gathered through the examination of financial reports, industry databases, interviews with banking specialists, and surveys. For the quantitative and qualitative data, statistical analysis and theme coding were used, respectively. The study aimed to provide significant insights to academia, the banking sector, and industry stakeholders by providing a comprehensive understanding of how technology adoption impacts the performance landscape of banks in Zambia. The findings revealed a positive correlation between technology adoption and financial performance with a Pearson’s two-tailed coefficient of 0.6. The study also investigated perceptions around IT platform stability and total bank efficiency, demonstrating a strong belief in the performance-enhancing potential of a reliable IT infrastructure.