neema Lyimo

Ms. neema Lyimo

Wuhan University, 430079,Wuhan, China

Research Focus & Metrics

Academic Career Length

8Years (2019-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.

19 November 2019 in Sustainability
Verified
Journal Article
Open access
PDF file
NSNeema Sumari
Neema Sumari
Gang XuGang Xu
Gang Xu
FUFanan Ujoh
Fanan Ujoh
PKProsper Korah
Prosper Korah
OEObas John John Ebohon
Obas John John Ebohon
neema Lyimoneema Lyimo
neema Lyimo
Sustainable urban planning is essential in mediating the natural and built environments globally, yet, there is little progress as regards its attainment in developing countries. Rapid and unplanned urbanization continue to threaten the sustainability of many cities in Africa. By selecting Morogoro Municipal Council (MMC) in Tanzania as an example, this study applied well-known remote sensing techniques to understand the dynamics of urban growth and the implications for sustainable urban planning. The study analyzes spatio-temporal characteristics for eighteen years (2000–2018) based on urban land density using gradient and grid-based analysis to further examine land use and urban land density nexus. The results indicate declining urban land densities with distance to the city center, indicating a less compact and fragmented development at the urban fringes; and northward development with limited development to the south of MCC. The knowledge and understanding of the patterns of spatio-temporal conditions, land use planning, and management interventions in MMC are necessary for addressing the inadequacies associated with rapid urbanization within the study area. On this basis, we propose a shift from the modernist to the communicative planning strategy that strongly integrates the urban social, economic, and environmental imperatives, while being adaptable to evolving realities. This plan should also aim to curtail urban sprawl and create a viable city system and economically prosperous city structure for MMC.

Verified
Journal Article
Open access
PDF file
neema Lyimoneema Lyimo
neema Lyimo
ZSZhenfeng Shao
Zhenfeng Shao
AAAlly Mgelwa Ally
Ally Mgelwa Ally
NTNana Yaw Danquah Twumasi
Nana Yaw Danquah Twumasi
Mehmet Orhan AltanMehmet Orhan Altan
Mehmet Orhan Altan
CSCamilius Sanga
Camilius Sanga
Besides OpenStreetMap (OSM), there are other local sources, such as open government data (OGD), that have the potential to enrich the modeling process with decision criteria that uniquely reflect some local patterns. However, both data are affected by uncertainty issues, which limits their usability. This work addresses the imprecisions on suitability layers generated from such data. The proposed method is founded on fuzzy logic theories. The model integrates OGD, OSM data and remote sensing products and generate reliable landfill suitability results. A comparison analysis demonstrates that the proposed method generates more accurate, representative and reliable suitability results than traditional methods. Furthermore, the method has facilitated the introduction of open government data for suitability studies, whose fusion improved estimations of population distribution and land-use mapping than solely relying on free remotely sensed images. The proposed method is applicable for preparing decision maps from open datasets that have undergone similar generalization procedures as the source of their uncertainty. The study provides evidence for the applicability of OGD and other related open data initiatives (ODIs) for land-use suitability studies, especially in developing countries.

4 June 2025 in Frontiers in Artificial Intelligence
Verified
Journal Article
Open access
PDF file
neema Lyimoneema Lyimo
neema Lyimo
KFKadeghe Goodluck Fue
Kadeghe Goodluck Fue
SMSilvia Francis Materu
Silvia Francis Materu
NKNdimile Charles Kilatu
Ndimile Charles Kilatu
JTJoseph Philipo Telemala
Joseph Philipo Telemala
Introduction: This study evaluates the potential of machine learning (ML) to predict and manage weather-sensitive waterborne diseases (WSWDs) in selected Tanzanian districts, focusing on environmental health officers' (EHOs) knowledge and perceptions. It explores EHOs' familiarity with information and communication technology (ICT) and artificial intelligence (AI)/ML, alongside challenges and opportunities for integrating AI-driven public health solutions.Methods: A census-style survey was conducted among EHOs in three district councils. A structured questionnaire, piloted in one district, was administered to 76 EHOs, achieving a 66% response rate. Data were analyzed using descriptive and inferential statistics to assess knowledge levels, perceptions, and gender-related differences.Results: Most EHOs were moderately familiar with ICT; however, only 54% had prior exposure to AI/ML concepts, and 64% reported limited AI familiarity. Among the variables examined, only prior exposure to AI/ML concepts and self-reported familiarity with AI demonstrated statistically significant associations with gender. Despite this, the majority recognized AI/ML's potential to improve disease prediction accuracy. Key barriers to ML adoption include inadequate technical infrastructure, data quality issues, and a shortage of expertise. Opportunities identified included utilizing historical disease data, integrating AI with meteorological information, and using satellite imagery for surveillance.Discussion: The study highlights frontline health workers' perceived barriers to ML adoption and suggests that gender influences awareness and engagement with AI and ML technologies. Strengthening technical capacity, improving data quality, and fostering cross-sector collaboration are critical for successful AI/ML integration. These insights offer a roadmap for resilience to WSWDs in developing countries like Tanzania through data-driven technologies.

3 January 2020 in Sustainability
Verified
Journal Article
Open access
PDF file
NTNana Yaw Danquah Twumasi
Nana Yaw Danquah Twumasi
CCChikondi Chisenga
Chikondi Chisenga
Nayyer SaleemNayyer Saleem
Nayyer Saleem
neema Lyimoneema Lyimo
neema Lyimo
Mehmet Orhan AltanMehmet Orhan Altan
Mehmet Orhan Altan
Decentralization problems in Africa have caused some infrastructure disparity between country capitals and distant districts. In Ghana, less public investment has created a gap between implementation results and theoretical benefits. Spectral indices are a good approach to extracting impervious surfaces, which is a good method of measuring urbanization. These are restricted by complexity, sensor limitation, threshold values, and high computational time. In this study, we measure the urbanization dynamics of Wa District in Ghana by applying a proposed method of impervious surface extraction index (ISEI), to evaluate the decentralization policy using Landsat images from 1984–2018 and a single S2A data. Comparing our proposed method with five other existing indexes, ISEI provided good discriminated results between target feature and background, with pixel values ranging between 0 and +1. Other indexes produced negative values. ISEI accuracy varied from 84.62–94.00% while existing indexes varied from 73.85–90.00%. Our results also showed increased impervious surface areas of 83.26 km2, which is about 7.72% of total area while the average annual urban growth was recorded as 4.42%. These figures proved that the quantification of decentralization is very positive. The study provides a foundation for urban environment research in the context of decentralization policy.

1 January 2019
Verified
Book Chapter
Closed access
CSCamilius A. Sanga
Camilius A. Sanga
neema Lyimoneema Lyimo
neema Lyimo
Kadeghe Goodluck FueKadeghe Goodluck Fue
Kadeghe Goodluck Fue
JTJoseph Philipo Telemala
Joseph Philipo Telemala
FKFredy Kilima
Fredy Kilima
MKMaulilio John Kipanyula
Maulilio John Kipanyula
Crowdsourcing can be viewed as a positive catalyst for effective results in many sectors of the economy including business, governance, agriculture, and health to name a few because it provides unlimited opportunities to people to share information among societies around the world. Despite some considerable efforts to adopt this concept in Tanzania, less has been done on its implementation in monitoring and evaluation of projects. This chapter proposes the development of a crowdsourcing platform as an essential step towards combating corruption, misuse, and embezzlement of funds. The developed crowdsourcing platform for monitoring and evaluation provides an up-to-date status of projects based on key indicators set and from such information, any member in particular organization can monitor and evaluate the progress of a given project. Results of this study show that the platform promotes transparency, collaboration, accountability, and has potential to motivate different actors or stakeholders in monitoring projects funded by government and donors.