Advances in deep learning have highlighted the need for models tailored for deployment in resource-constrained environments (RCEs), where memory and processing limitations present significant challenges, such as those found in mobile devices, Internet of things (IOT) devices, and embedded systems. This paper introduces GRMobiNet, a novel deep neural network (DNN) model designed to address these challenges in image classification tasks by balancing computational complexity with model accuracy in RCE settings. The model focuses on key performance goals inspired by previous state-of-the-art models, aiming to achieve a better balance between complexity and accuracy. These goals include reducing the model's computational complexity to fewer than 4 million parameters, limiting memory usage to under 16 megabytes, and achieving an accuracy greater than 80%. By meeting these objectives, GRMobiNet enhances both the effectiveness and efficiency of deep neural network deployment in RCE settings. GRMobiNet builds upon MobileNet as its baseline, incorporating advanced techniques such as depthwise separable convolutions, compound scaling, global average pooling, and quantization to optimize performance. Trained on ImageNet-10, a subset of ImageNet-1K, the model underwent rigorous performance evaluation. Experimental results demonstrate that GRMobiNet achieves its performance objectives, with a computational complexity of 3.2 million parameters, memory utilization of 12.6 megabytes, and a prediction accuracy of 92%, validating its suitability for RCEs. This research presents a scalable framework for balancing accuracy and computational efficiency, with significant implications for RCE devices. In future work, GRMobiNet will be tested on commercially available RCE mobile devices using real-world images to assess its practicality and evaluate its performance in terms of accuracy, confidence, and inference time for image classification in real-world scenarios.

Literature show that there are limited factors for existing models in e-learning systems’ adoption. This has raised an increasing sensible debate about factors affecting successful adoption of e-leaning systems in universities in developing world particularly in Tanzania. This preliminary study aimed at exploring multiple factors for successful adoption of e-learning systems in universities in learner perspective, using DeLone and McLean (2003) IS success model as a base model. This study was conducted by collecting data randomly, using the questionnaire from students of Open Universities of Tanzania (OUT) with response rate of 0.83 in a cross-sectional study and later analyzed through content validity, reliability, and criterion-based predictive validity. The preliminary analysis shows that there are twelve distinctive factors affecting e-learning systems’ adoption in universities in Tanzania. This finding suggests more empirical research studies to follow it up, to cement and generalize this case and validate the proposed model in large scale. The novelty of this research lies on the number and uniqueness of factors found.

Observed images with bare eyes are always different than the acquired ones using an imaging system since the captured images are considered as the degraded versions of the original scene. These degradations may vary between image noise, lighting defects and blur. Therefore, this article addresses the field of computer forensics with image deblurring as the latent details that are indeed present in the captured images are concealed due to the blurring artifact. Moreover, the constant types of blur that are being dealt with in forensics are the motion and the out-of-focus blur. The motion blur occurs due to the motion of the recorded objects or the camera during the capturing process. The out-of-focus blur occurs due to lens defocusing errors. Different examples are provided to focus on the importance of deblurring forensic images. In addition, concise commentaries on deblurring methods, applications and blur types are deliberated for additional knowledge.