Point of Sale terminals play a significant role in revenue collection and have become rampant to Tanzanian Local Government Authorities. Point of Sale systems monitors cash flow, transactions, and price control while reducing human error and managing staff, customers, and inventory. However, Point of Sale systems are vulnerable to fake receipts, thus reducing revenue collections among Local Government Authorities. The cross-sectional Design was used to facilitate knowledge for the subsequent data collection. Data were collected from 300 respondents in Mbeya and Songwe regions using purposive and simple random sampling. 70% of respondents reported that fake receipt is the major factor affecting revenue collection, followed by lack of training (20%) and security (8%). In this study, we propose a mobile-based solution to enhance revenue collection in Local Government Authorities by addressing major factors affecting revenue collection. The developed mobile application was evaluated and validated; Whereby the results confirm that the designed tool is effective against money fraud, transaction errors, human errors, and defaulters with minimal resource usage. Hence, the designed mobile application can be applied as an auditing tool to reduce money fraud and increase revenue collection for the Local Government Authorities

Late blight (LB) disease causes significant annual losses in tomato production. Early identification of this disease is crucial in halting its severity. This study aimed to leverage the strength of Convolutional Neural Networks (CNNs) in automated prediction of tomato LB. Through transfer learning, the MobileNetV3 model was trained on high-quality, well-labeled images from Kaggle datasets. The trained model was tested on different images of healthy and infected leaves taken from different real-world locations in Mbeya, Arusha, and Morogoro. Test results demonstrated the model's success in identifying LB disease, with an accuracy of 81% and a precision of 76%. The trained model has the potential to be integrated into an offline mobile app for real-time use, improving the efficiency and effectiveness of LB disease detection in tomato production. Similar methods could also be applied to detect other tomato infections. Keywords:  MobileNets; convolutional neural networks; plant diseases detection; image classification; transfer learning

Machine type communication devices proposed as one of the substantial data collections in the 5G of wireless networks. However, the existing mobile communication network is not designed to handle massive access from the MTC devices instead of human type communication. In this context, we propose the device-to-device communication assisted a mobile terminal (smartphone) on data computing, focusing on data generated from a correlated source of machine type communication devices. We consider the scenario that the MTC devices after collecting the data will transmit to a smartphone for computing. With the limitation of computing resources at the smartphone, some data are offloaded to the nearby mobile edge-computing server. By adopting the sensing capability on MTC devices, we use a power exponential function to compute a correlation coefficient existing between the devices. Then we propose two grouping techniques K-Means and hierarchical clustering to combine only the MTC devices, which are spatially correlated. Based on this framework, we compare the energy consumption when all data processed locally at a smartphone or remotely at mobile edge computing server with optimal solution obtained by exhaustive search method. The results illustrated that; the proposed grouping technique reduce the energy consumption at a smartphone while satisfying a required completion time.

No abstract

The Internet of Medical Things (IoMT) connects a huge amount of smart sensors with the Internet for healthcare service provisioning. IoMT’s privacy-preserving becomes a challenge considering the life-saving data collected and transferred through IoMT. Traditional privacy protection techniques use centralized management strategies, which lead to a single point of failure, lack of trust, state modification, information disclosure, and identity theft. Edge computing enables local computation of IoMT data, which reduces traffic to the cloud and also helps in accomplishing latency-sensitive healthcare applications and services. This paper proposes a novel framework (i.e., SecureMed) that uses blockchain-based distributed authentication implemented at the edge cloudlets to enforce privacy protection. In SecureMed, IoMT devices interact with edge cloudlets using smart contracts. It uses trusted edge nodes to implement an authentication algorithm that uses public/private key matching to authenticate IoMT. Experimental evaluation performed using the Pythereum blockchain shows that SecureMed outperforms the traditional blockchain scheme based on latency, bandwidth consumption, deployment time, scalability, and accuracy. Therefore, it can be used to protect the edge-enabled IoMT from privacy attacks and to ensure end-to-end healthcare service provisioning.