Farian S. Ishengoma

Farian S. Ishengoma

Auto-generated profile, based on publicly available information

Farian S. Ishengoma

Department of Informatics and Information Technology, Sokoine University of Agriculture, Morogoro, Tanzania

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 June 2024 in Heliyon
Verified
Journal Article
Open access
FIFarian S. Ishengoma
Farian S. Ishengoma
neema Lyimoneema Lyimo
neema Lyimo
Detecting crop diseases before they spread poses a significant challenge for farmers. While both deep learning (DL) and computer vision are valuable for image classification, DL necessitates larger datasets and more extensive training periods. To overcome the limitations of working with constrained datasets, this paper proposes an ensemble model to enhance overall performance. The proposed ensemble model combines the convolution neural network (CNN)-based models as feature extractors with random forest (RF) as the output classifier. Our method is built on popular CNN-based models such as VGG16, InceptionV3, Xception, and ResNet50. Traditionally, these CNN-based architectures are referred to as one-way models, but in our approach, they are connected in parallel to form a two-way configuration, enabling the extraction of more diverse features and reducing the risk of underfitting, particularly with limited datasets. To demonstrate the effectiveness of our ensemble approach, we train models using the grape leaf dataset, which is divided into two subsets: original and modified. In the original set, background removal is applied to the images, while the modified set includes preprocessing techniques such as intensity averaging and bilateral filtering for noise reduction and image smoothing. Our findings reveal that ensemble models trained on modified images outperform those trained on the original dataset. We observe improvements of up to 5.6 % in accuracy, precision, and sensitivity, thus validating the effectiveness of our approach in enhancing disease pattern recognition within limited datasets.

9 July 2023
Verified
Book Chapter
Closed access
PDF file
FIFarian S. Ishengoma
Farian S. Ishengoma
IRIdris A. Rai
Idris A. Rai
IGIgnace Gatare
Ignace Gatare

19 July 2026
Verified
Conference Paper
Open access
JTJoseph P. Telemala
Joseph P. Telemala
ONOnesmo S. Nyinondi
Onesmo S. Nyinondi
NLNeema N. Lyimo
Neema N. Lyimo
BNBaraka W. Nyamtiga
Baraka W. Nyamtiga
FIFarian S. Ishengoma
Farian S. Ishengoma
WMWema L. Msigwa
Wema L. Msigwa
Despite major advances in information retrieval (IR) and language technologies, speakers of extremely low-resource ethnic community languages (ECLs) remain largely excluded from digital information access. With Tanzania having over 120 languages, yet most IR systems and digital assistants primarily support English and, to a limited extent, Kiswahili. This disproportionately affects rural populations (over 65%), where ECLs are used alongside Kiswahili in daily life. This paper presents the ongoing Ethnic Voices initiative, which addresses this gap by building foundational text and speech resources explicitly relevant to IR research in extremely low-resource multilingual settings. The project targets six ECLs in Tanzania, with current data collection completed for Hehe and Luguru. Data collection from the two ECLs has produced over 800 Kiswahili-ECL parallel sentences per language and over 95 hours of speech. Preliminary survey results show strong demand for multilingual and voice-based access to information. It further identifies language barriers as a primary limitation of existing English-centric IR systems. This also paper discusses the IR implications of these findings and outlines directions toward inclusive retrieval and evaluation in extremely low-resource languages. Beyond resource creation, we position the collected dataset as IR-enabling infrastructure that supports the formulation of retrieval tasks, the development of baseline systems, and the design of evaluation protocols in benchmark-scarce, extremely low-resource multilingual settings.

7 February 2023 in Research Square
Verified
Preprint
Open access
PDF file
FIFarian S. Ishengoma
Farian S. Ishengoma
NLNeema N. Lyimo
Neema N. Lyimo
Identifying and detecting crop diseases before they spread is a critical task for any farmer. Deep learning and computer vision are both useful for learning image features used in image classification tasks; however, deep learning takes a long time to train. In this paper, we propose an ensemble model for detecting pests on grape leaf images that employs a convolution neural network (CNN) as a feature extractor and a random forest (RF) as a classifier. CNN-based models VGG16, InceptionV3, Xception, and ResNet50 are arranged in parallel of two- and three-pathway configurations to extract more features and given to the RF for classification, and their accuracy is compared to a one-way model. Using the same data, we found that arranging CNN-based models in parallel configurations improves accuracy by 3.43% for two-pathway models and 6.37% for three-pathway models. Moreover, the best model in the one-way setting achieved 89.22% accuracy, while the best models in the two- and three-pathways settings achieved 92.65% and 95.59% accuracy, respectively.

4 January 2023
Verified
Book Chapter
Closed access
PDF file
FIFarian S. Ishengoma
Farian S. Ishengoma
IRIdris A. Rai
Idris A. Rai
IGIgnace Gatare
Ignace Gatare