Computer Sciencehttp://ir.haramaya.edu.et//hru/handle/123456789/1442024-03-28T17:02:37Z2024-03-28T17:02:37ZA FRAMEWORK FOR HEALTH INFORMATION SHARING AND PRIVACY PRESERVATION USING INFORMATION HIDING AND DIFFERENTIAL PRIVACY.Abrahim Abdo(Ph.D.) Faizur Rashidhttp://ir.haramaya.edu.et//hru/handle/123456789/71992024-01-02T06:45:00Z2023-08-01T00:00:00ZA FRAMEWORK FOR HEALTH INFORMATION SHARING AND PRIVACY PRESERVATION USING INFORMATION HIDING AND DIFFERENTIAL PRIVACY.
Abrahim Abdo; (Ph.D.) Faizur Rashid
Health information exchanges (HIEs) are an important part of the healthcare system. The
World Health Organization emphasizes the importance of security standards in managing
personal health data, as privacy concerns among healthcare consumers are increasing. HIPAA
prioritizes unauthorized disclosures, improper disposal, access, and other IT security and
privacy breaches of protected health information (PHI). The study demonstrates secure health
information sharing methods, ensuring trust and patient privacy through AES-128-CBC and
VSS-XOR, and integrating authentication, authorization, and access control with attributes for
user tracking. We perform further comparative analyses based on the visual cryptography in
LSB and DWT algorithms. PSNR results describe the similarity between the recovered secret
image and the original image. The novel health data sharing method using Named Entity
Recognition (NER), NER BiLSTM, provides 94% more accurate PII prediction than current
evidence on medical text prediction. The differential privacy application evaluates noise
levels to protect patients' privacy by removing or replacing patients and was compared using
word2vec and GloVe 300-dimensional embedding approaches. Word2vec performed better
semantically, while GloVe outperformed due to its support for a wide range of epsilon values,
ensuring patient privacy. The effectiveness and viability of the suggested scheme are
demonstrated by experiments and comparisons of the metrics. It is demonstrated that our
suggested scheme can withstand statistical analysis and counterattacks. By combining legal
agreements and technology to ensure meaningful information exchange, our developed
protocol complied with information security and HIPPA privacy basic rules
111p.
2023-08-01T00:00:00ZAFAAN OROMO GRAMMAR CHECKER USING HYBRID APPROACHTAJIR AMIN ALITeklu Urgeessa (PhD)Elias Debelohttp://ir.haramaya.edu.et//hru/handle/123456789/71712023-12-08T12:05:41Z2023-08-01T00:00:00ZAFAAN OROMO GRAMMAR CHECKER USING HYBRID APPROACH
TAJIR AMIN ALI; Teklu Urgeessa (PhD); Elias Debelo
A grammar checker is one of the basic NLP applications used to check whether sentences are
grammatically correct or not. To solve the Afaan Oromo grammar error problem, an Afaan
Oromo grammar checker using a hybrid approach is proposed. To achieve the goal of this study,
each statistical and rule-based approach acts as a module. Afaan Oromo's sentences were
checked for word order errors using a statistical grammar checker module. While a rule-based
grammar checker module is used to check morphological agreement errors. The rule-based
grammar checker module was tested after the statistical grammar checker module. Because if
the word order of the sentence is correct. Language grammar rules can be used to resolve errors
in morphological agreement errors. In the statistical approach, the bi-gram statistical technique
checks the grammatical correctness of a sentence by calculating the probability of a bigram
sequence of tags in both the training and test datasets. If a sentence is found to be free of word
order errors, a rule-based module is run to check the sentence for morphological agreement
errors and make suggestions if there are errors. For the experiment, the POS tagset from (Emiru
2016) was used. POS tagger corpus was manually prepared from 2000 sentences collected from
OBN. The tagger used 85% for training and 15% for testing the HMM Viterbi model. A tag
sequence corpus of 570 sentences was manually prepared and used by the statistical bigram
model. To handle agreement errors, 150 rules were manually created and used by a rule-based
grammar checker. The system was implemented using the Python programming language
Python3 and Jupyter notebook tools. In the implementation of this work, the prepared and
collected data were first preprocessed to be ready for use in each module of the grammar
checker. From the conducted experiment, the researcher manually prepared 255 sentences and
measured the average performance evaluation of the Afaan Oromo grammar checker using
hybrid approaches. The evaluated result in the test sentences was 82% precision, 76% recall,
and 79% of F-measure. Using a hybrid approach for the Afaan Oromo grammar checker
achieves good results. The use of a high-quality Afaan Oromo corpus and a deep learning
approach will be the future work to improve the performance
82
2023-08-01T00:00:00ZSKELETON-BASED ETHIOPIAN SIGN LANGUAGE RECOGNITION USING DEEP LEARNINGDeme KumaMillion Meshesha (Ph.D.)Kidane W/Maryam (M.Sc.)http://ir.haramaya.edu.et//hru/handle/123456789/69072023-11-20T07:27:03Z2023-11-01T00:00:00ZSKELETON-BASED ETHIOPIAN SIGN LANGUAGE RECOGNITION USING DEEP LEARNING
Deme Kuma; Million Meshesha (Ph.D.); Kidane W/Maryam (M.Sc.)
Recent reports show that there are over 1.5 billion people around the globe with hearing impairment, and here in Ethiopia, their number is estimated to be over 1.2 million. These people use Sign Language as a way of communication using manual and non-manual signs. However, Sign Language is only understood by the deaf community and some of their families. This creates a communication gap between them and the rest of the world. Although interpreters try to fill the gap, it is not enough compared to the communication demand. Hence, Automatic Sign Language Recognition (ASLR) is being studied for various Sign Languages in the world to fill the communication gap. ASLR methods involved techniques ranging from traditional machine learning to modern deep learning. Regarding Ethiopian Sign Language, few attempts were made to automate the recognition of Ethiopian Sign Language. However, they were found to be environment and signer dependents. These gaps hinder the journey to commercialize fully automated Sign Language Recognition products. Consequently, this study proposes an environment and signer invariant Sign Language Recognition model. The model first extracts skeletal key-points from the signer using MediaPipe, which is Google’s cross-platform pipeline framework that helps to detect and track human pose, face landmarks, and hands. After preprocessing the skeletal key-points information, feature extraction and learning are performed using deep learning architectures; Convolutional Neural Network followed by Long Short-Term Memory (CNN-LSTM), Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Units (GRU). In this study, the models were trained to classify twenty (20) isolated dynamic Ethiopian Sign Language signs. A total of 5600 video samples were collected from volunteer students at Haramaya University and used to train and test the deep learning-based models. First, all the models were trained and tested in a signer-dependent mode where GRU outperformed the other deep learning algorithms with 94% recognition accuracy. The outperforming GRU-based model was further tested in signer-independent mode and attained 73% recognition accuracy. The outcome of this study shows that Ethiopian Sign Language can be recognized in real-time within dynamic environments. It also implied that signer-independence can be achieved. This study attempted to take the signer-independence of ASLR models up to some level. However, further studies are required to recognize continuous signs in a fully open environment. Therefore, the technique implemented
xiv
to detect and track key-points in this study should further be investigated to recognize continuous EthSL.
118
2023-11-01T00:00:00ZSEVERITY CLASSIFICATION OF COMMON RUST MAIZE LEAF DISEASE AND PESTICIDES DOSE RECOMMENDATION USING DEEP NEURAL NETWORKZemzem MohammedAbebe Belay (PhD)Faizur Rashid (PhD)http://ir.haramaya.edu.et//hru/handle/123456789/69062023-11-20T07:16:26Z2023-11-01T00:00:00ZSEVERITY CLASSIFICATION OF COMMON RUST MAIZE LEAF DISEASE AND PESTICIDES DOSE RECOMMENDATION USING DEEP NEURAL NETWORK
Zemzem Mohammed; Abebe Belay (PhD); Faizur Rashid (PhD)
Maize is one of the most widely grown cereal crops in Ethiopia and the world. Maize common
rust, which is a common problem in the study area, is caused by the fungus Puccinia sorghi,
and it can severely affect the yield and quality of maize. It typically causes for the losses of 23-
65%. The traditional severity quantification of rust involves manual diagnosis and
identification, which can be time-consuming, expensive and sometimes leading to errors. In
this research, we proposed to develop a CNN-based model for quantifying maize common rust
severity and recommend suitable fungicide doses.
The proposed system includes data pre-processing, image segmentation, image augmentation,
model training and feature extraction, severity classification, performance evaluation and
pesticide dose recommendation. A dataset of 8000 maize leaf images, which were collected
from Haramaya University Rare Research Center, were used for training the CNN algorithm
and develop models. After exhaustive training of algorithm in different ratios, we found
optimum results at 70%, 15%, and 15% for training, testing and validation datasets,
respectively.
In this study, we evaluated the performance of five deep learning models (CNN types) -
Resnet50, VGG19, VGG16, CNN, and AlexNet - for classifying the severity of maize common
rust and recommending pesticide doses. Severity refers to the degree of damage caused by a
disease or pest to a particular crop. We conducted two experiments, one using dropout, batch
normalization, and early stopping techniques and the other without them, to test the impact of
regularization on model performance. Our results show that the models trained with
regularization achieved better accuracy and convergence speed than the ones without it. Among
the models, Resnet50 exhibited the best overall performance, with an average F1-score of 97%
and a mean absolute error of 0.096, followed by VGG-19 (F1-score 95%), AlexNet (F1-score
94%), VGG-16 (93%), and CNN (F1-score 92%). Using a CNN model with a Gradio interface
accurately recommended the appropriate dose of fungicide based on the severity of rust in the
maize leaves. Our findings suggest that deep learning models can be effective tools for maize
disease diagnosis and management, and that regularization techniques can enhance their
robustness and generalization performance
100
2023-11-01T00:00:00Z