Research Article
Predicting Depression in Women Using Deep Learning Techniques
Issue:
Volume 2, Issue 3, June 2026
Pages:
189-195
Received:
23 February 2026
Accepted:
3 March 2026
Published:
12 May 2026
Abstract: Depression is a significant global health issue with a notably higher prevalence in women. However, many predictive models using artificial intelligence (AI) overlook gender-specific symptom patterns, limiting their sensitivity and effectiveness for female populations. This study addresses this gap by developing and evaluating a multimodal, gender-specific deep learning framework designed to predict depression exclusively in women. Leveraging the female subset of the Distress Analysis Interview Corpus (DAIC-WOZ) dataset, the study utilizes a late-fusion architecture that integrates four distinct data streams: textual transcripts, acoustic features, visual facial cues, and tabular clinical data (PHQ-8 scores). The model employs specialized neural network branches for each modality- a Transformer (DistilBERT) for text, a Bidirectional LSTM (BiLSTM) for audio, a Temporal CNN for visual sequences, and a Multi-Layer Perceptron (MLP) for tabular data before concatenating their embeddings for a final prediction. The results demonstrate the superior performance of the multimodal approach, achieving an F1-score of 089 and an ROC-AUC of 0.92, significantly outperforming unimodal baselines. Ablation studies revealed that textual data was the most influential modality, with its removal causing a performance degradation of over 15% in the F1-score. Acoustic features were identified as the second most critical predictor, underscoring the importance of both linguistic content and vocal prosody.
Abstract: Depression is a significant global health issue with a notably higher prevalence in women. However, many predictive models using artificial intelligence (AI) overlook gender-specific symptom patterns, limiting their sensitivity and effectiveness for female populations. This study addresses this gap by developing and evaluating a multimodal, gender-...
Show More
Research/Technical Note
Space Architecture: The New Frontier for Nigeria
Chukwuka Prosper Chukwuebuka*
,
Chinwe Sam-Amobi,
Justus Chukwunonyerem,
Ejianya Chiogo Obumneme,
Odira Eze Cletus,
Ezeoyili Nnamdi Martin
Issue:
Volume 2, Issue 3, June 2026
Pages:
196-202
Received:
18 May 2026
Accepted:
3 June 2026
Published:
26 June 2026
DOI:
10.11648/j.scif.20260203.12
Downloads:
Views:
Abstract: The New Frontier; space architecture is an emerging and specialized field in the space sector. Space architecture plays a vital role in the development of facilities like space research stations, analog habitats, and disaster-resilient structures. It also involves the study of human factors and how humans interact with their environment in confined and extreme conditions. While the ultimate goal of space architecture is to design for outer space, a significant portion of the work is done right here on Earth. Nigeria is a hub of diverse talent in Africa and the globe, particularly in the creative sectors, with a young tech-savvy workforce and a growing number of global professionals ready to drive innovative ideas. The practice of space architecture in Nigeria will open a new world of possibilities in space research and exploration. This paper utilizes a qualitative research methodology; the paper explains the necessity of integrating space architecture into the National Space Research and Development Agency’s vision and mission, so as to drive space science development in Nigeria. It highlights the current Space Centres in Nigeria, identifies key challenges, and proposes strategic pathways for integrating space architecture into Nigeria’s space development plans. The recommendations include the introduction of space architecture as a science field in Nigeria. The National Space Research and Development Agency (NASRDA), as the lead agency in collaboration with the National Universities Commission (NUC), will be pivotal to the development of this field in the higher institutions and in the establishment of a specialized centre for space architecture in Nigeria.
Abstract: The New Frontier; space architecture is an emerging and specialized field in the space sector. Space architecture plays a vital role in the development of facilities like space research stations, analog habitats, and disaster-resilient structures. It also involves the study of human factors and how humans interact with their environment in confined...
Show More
Research Article
Comparative Evaluation of Satellite Rainfall Estimates Blended with Observation over Ethiopian Blue Nile Basin
Issue:
Volume 2, Issue 3, June 2026
Pages:
203-217
Received:
3 June 2026
Accepted:
13 June 2026
Published:
29 June 2026
DOI:
10.11648/j.scif.20260203.13
Downloads:
Views:
Abstract: The Ethiopian Blue Nile Basin exhibits pronounced rainfall variability, and projected climate change is expected to further amplify this uncertainty, with significant implications for water resource availability, particularly under conditions of growing demand. This study was undertaken to examine the spatiotemporal variability of rainfall over the Ethiopian Blue Nile Basin through statistical and spatial analysis of historical rainfall records, with the objective of assessing rainfall distribution patterns and evaluating data reliability. The aim of this study was, therefore, to compare and validate the performance of Kiremt and Annual rainfall Gauge-Blended Product (ENACT) with Satellite products (CHIRPS, ARC2, PERSIANN-CDR, TAMSAT, and GPCC) that were collected from satellite during the period of 1991-2020 over the Ethiopian Blue Nile Basin. At the seasonal scale, CHIRPS achieved the highest correlation coefficient (R = 0.96), indicating strong agreement with gauge observations, together with the lowest RMSE (32.59 mm) and a near-optimal bias value (BIAS = 1.08). The product also exhibited excellent rainfall event detection capability, with POD, CSI, and VHI values of 0.97, 0.93, and 0.99, respectively, while maintaining relatively low FAR (0.04) and VFAR (0.04). Similarly, GPCC and TAMSATv3.1 showed relatively strong performance, whereas ARC2 exhibited comparatively lower skill, particularly in terms of RMSE and volumetric indices. At the annual scale, CHIRPS again outperformed the other rainfall products, recording the highest correlation coefficient (R = 0.85), the lowest RMSE (47.61 mm), and near-unity categorical and volumetric statistics, including POD = 1.00, CSI = 1.00, VHI = 1.00, and VCSI = 0.99. Although GPCC and TAMSATv3.1 also demonstrated strong annual performance, ARC2 showed relatively weaker agreement with observed rainfall, characterized by lower correlation (R = 0.60) and higher RMSE (87.64 mm). The results of this study provide crucial information for water resources management, which directly have impacts on human socio-economic life, and environment. It can be used by different stakeholders, researchers, and policy makers to inform decision-making process.
Abstract: The Ethiopian Blue Nile Basin exhibits pronounced rainfall variability, and projected climate change is expected to further amplify this uncertainty, with significant implications for water resource availability, particularly under conditions of growing demand. This study was undertaken to examine the spatiotemporal variability of rainfall over the...
Show More
