Olasimbo Ayodeji Arigbabu

Olasimbo Ayodeji Arigbabu

AI agents are commonly evaluated using task success, reward, latency, and cost. These metrics are useful, but they often miss important aspects of agent behavior: whether an agent explores too much, repeats itself too rigidly, uses tools effectively, reduces uncertainty over time, or remains robust across repeated runs. This paper proposes Entropy-Based Evaluation of AI Agents (EEA), a lightweight framework for measuring agent behavior through entropy. Rather than treating intelligence as only final task completion, EEA studies the structure of the agents decision process. The framework introduces action entropy, trajectory entropy, tool entropy, information gain, exploration efficiency, and robustness entropy. These metrics are intended to complement, not replace, traditional evaluation methods. We also present a practical Python implementation designed to integrate with agent frameworks such as LangChain, Google ADK, custom agent loops, and stored observability traces.

Olasimbo Ayodeji Arigbabu

Human activity recognition serves an important part in building continuous behavioral monitoring systems, which are deployable for visual surveillance, patient rehabilitation, gaming, and even personally inclined smart homes. This paper demonstrates our efforts to develop a collaborative decision fusion mechanism for integrating the predicted scores from multiple learning algorithms trained on smartphone sensor based human activity data. We present an approach for fusing convolutional neural network, recurrent convolutional network, and support vector machine by computing and fusing the relative weighted scores from each classifier based on Tsallis entropy to improve human activity recognition performance. To assess the suitability of this approach, experiments are conducted on two benchmark datasets, UCI-HAR and WISDM. The recognition results attained using the proposed approach are comparable to existing methods.

Olasimbo Ayodeji Arigbabu, Sharifah Mumtazah Syed Ahmad, Wan Azizun Wan Adnan et al.

Gender recognition from unconstrained face images is a challenging task due to the high degree of misalignment, pose, expression, and illumination variation. In previous works, the recognition of gender from unconstrained face images is approached by utilizing image alignment, exploiting multiple samples per individual to improve the learning ability of the classifier, or learning gender based on prior knowledge about pose and demographic distributions of the dataset. However, image alignment increases the complexity and time of computation, while the use of multiple samples or having prior knowledge about data distribution is unrealistic in practical applications. This paper presents an approach for gender recognition from unconstrained face images. Our technique exploits the robustness of local feature descriptor to photometric variations to extract the shape description of the 2D face image using a single sample image per individual. The results obtained from experiments on Labeled Faces in the Wild (LFW) dataset describe the effectiveness of the proposed method. The essence of this study is to investigate the most suitable functions and parameter settings for recognizing gender from unconstrained face images.