Samy S. Abu-Naser

This study presents a neural network-based model for predicting smoke potential in a specific area using a Kaggle-derived dataset with 15 environmental features and 62,631 samples. Our five-layer neural network achieved an accuracy of 89.14% and an average error of 0.000715, demonstrating its effectiveness. Key influential features, including temperature, humidity, crude ethanol, pressure, NC1.0, NC2.5, SCNT, and PM2.5, were identified, providing insights into smoke occurrence. This research aids in proactive smoke mitigation and public health protection. The model's accuracy and feature analysis empower decision-makers, with potential applications in real-time smoke event monitoring and preparedness strategies. This work contributes to the field of air quality forecasting and environmental stewardship, offering a data-driven approach to address smoke-related challenges and enhance community well-being.

Abstract: This research delves into the utilization of Artificial Neural Networks (ANNs) as a powerful tool for predicting the overall ratings of books by leveraging a diverse set of attributes. To achieve this, we employ a comprehensive dataset sourced from Goodreads, enabling us to thoroughly examine the intricate connections between the different attributes of books and the ratings they receive from readers. In our investigation, we meticulously scrutinize how attributes such as genre, author, page count, publication year, and reader reviews influence a book's overall rating. Through rigorous analysis and experimentation, we construct an advanced ANN model tailored for predictive analysis in the realm of book ratings. The outcomes of our study reveal the remarkable potential of ANNs in this domain. The ANN model exhibits an impressive level of accuracy when it comes to forecasting book ratings, underlining the efficacy and promise of artificial neural networks in enhancing our understanding and prediction of book evaluations. This research opens up new avenues for leveraging machine learning techniques to gain deeper insights into the dynamics of book ratings and reader preferences.

Abstract: This research explores the application of artificial neural networks (ANNs) in predicting cancer using a synthetically generated dataset designed for research purposes. The dataset comprises 10,000 pseudo-patient records, each characterized by gender, age, smoking history, fatigue, and allergy status, along with a binary indicator for the presence or absence of cancer. The 'Gender,' 'Smoking,' 'Fatigue,' and 'Allergy' attributes are binary, while 'Age' spans a range from 18 to 100 years. The study employs a three-layer ANN architecture to develop a predictive model. The achieved accuracy of 97.24% and a low loss value of 0.02 indicate promising performance. Further analysis involves a comprehensive examination of the confusion matrix, precision, recall, and F1 score metrics, along with the ROC curve and AUC score, to provide a detailed understanding of the model's strengths and weaknesses. Additionally, considerations for cross-validation, hyperparameter tuning, and interpretability are discussed. It is emphasized that while the synthetic nature of the dataset allows for controlled experimentation, results should be cautiously interpreted and validated on authentic clinical data before extrapolation to real-world medical scenarios. This research serves as a valuable contribution to the exploration of predictive models for cancer detection, encouraging continued investigation and development in the field.

The study aimed to identify the leadership features and their relationship to increasing achievement motivation among Palestinian police employees in Gaza Strip in light of the Corona pandemic. To achieve the study’s objectives, the researchers used the descriptive method in its analytical method, using a questionnaire applied to the police officers at the Central Governorate Police Station, whose number is (113) individuals. They were chosen in a stratified, random manner, and the study resulted in a set of results, the most important of which is that the effect of leadership characteristics of Palestinian police employees in Gaza Strip, which came with a relative weight (76.20%), which is, to a large extent, the level of increase in achievement motivation among employees in the Palestinian Police in Gaza Strip. Gaza under the outbreak of the Corona epidemic? Which came with a relative weight (82.40%), which is to a large extent. While it resulted in a positive correlation between the impact of leadership characteristics and the increase in achievement motivation, there are no statistically significant differences between the averages of the study sample's estimates about the impact The leadership characteristics of the Palestinian Police in Gaza Strip are attributed to the variable of the age group, academic qualification, scientific specialization, scientific experience. There are no statistically significant differences between the averages of the estimates of the individuals of the study sample about The achievement motivation in the Palestinian Police in Gaza Strip is attributable to a variable, age group, academic qualification, scientific specialization, scientific experience, and in light of these results the researchers suggested a set of recommendations, the most important of which are: The need to tighten penalties for individuals by the Central Governorate Police Station for violating the instructions issued by the Ministry Interior In light of the outbreak of the Corona epidemic, increased interest in preparing and organizing specialized training courses and programs in the field of dealing with all different segments in order to preserve the lives of people from the Corona epidemic.

Abstract: In, this research embodies the spirit of interdisciplinary collaboration, bringing together data science, healthcare, and public health to address one of the most significant global health challenges in recent history. The achievements of this study underscore the potential of advanced machine learning techniques to enhance our understanding of the pandemic and guide effective decision-making. As we navigate the ongoing battle against COVID-19 and prepare for future health emergencies, the lessons learned from this research serve as a testament to the power of data-driven insights and the unwavering commitment of the global scientific community in the face of adversity.

Abstract Alzheimer's disease has spread insanely throughout the world. Early detection and intervention are essential to improve the chances of a positive outcome. This study presents a new method to predict a person's likelihood of developing Alzheimer's using a neural network model. The dataset includes 373 samples with 10 features, such as Group,M/F,Age,EDUC, SES,MMSE,CDR ,eTIV,nWBV,Oldpeak,ASF.. A four-layer neural network model (1 input, 2 hidden, 1 output) was trained on the dataset and achieved an accuracy of 98.10% and an average error of 0.01. This study provides a valuable tool for early detection and intervention of Alzheimer's, thus contributing to the field of health and medicine.

Abstract: The emergence of the novel coronavirus (COVID-19) in 2019 has presented the world with an unprecedented global health crisis. The rapid and widespread transmission of the virus has strained healthcare systems, disrupted economies, and challenged societies. In response to this monumental challenge, the intersection of technology and healthcare has become a focal point for innovation. This research endeavors to leverage the capabilities of Artificial Neural Networks (ANNs) to develop an advanced predictive model for forecasting the spread of COVID-19. It involves the collection, analysis, and integration of diverse datasets encompassing epidemiological, clinical, and social factors that influence the virus's dissemination.

Accurate assessment and comprehension of smoking behavior are pivotal for elucidating associated health risks and formulating effective public health strategies. In this study, we introduce an innovative approach to predict and analyze smoking prevalence using an artificial neural network (ANN) model. Leveraging a comprehensive dataset spanning multiple years and geographic regions, our model incorporates various features, including demographic data, economic indicators, and tobacco control policies. This research investigates smoking trends with a specific focus on gender-based analyses. These findings are pivotal for enhancing public health initiatives aimed at mitigating tobacco use, assessing associated health risks, and mitigating smoking-related diseases.

The aim behind analyzing the Goodreads dataset is to get a fair idea about the relationships between the multiple attributes a book might have, such as: the aggregate rating of each book, the trend of the authors over the years and books with numerous languages. With over a hundred thousand ratings, there are books which just tend to become popular as each day seems to pass. We proposed an Artificial Neural Network (ANN) model for predicting the overall rating of books. The prediction is based on these features (bookID, title, authors, isbn, language_code, isbn13, # num_pages, ratings_count, text_reviews_count), which were used as input variables and (average_rating) as output variable for our ANN model. Our model were created, trained, and validated using data set in JNN environment, which its title is “Goodreads-books”. Model evaluation showed that the ANN model is able to predict correctly 99.78% of the validation samples.

Abstract: In this study, we explore the possibility of classifying the plant species. We collected the plant species from Kaggle website. This dataset encompasses 544 samples, encompassing 136 distinct plant species. Recent advancements in machine learning, particularly Artificial Neural Networks (ANNs), offer promise in enhancing plant Species classification accuracy and efficiency. This research explores plant Species classification, harnessing neural networks' power. Utilizing a rich dataset from Kaggle, containing 544 entries, we develop and evaluate a neural network model. Our neural network, featuring a single hidden layer, achieves remarkable results—a staggering 100% accuracy and a minute average error rate of 0.002. Beyond performance metrics, we delve into the intricacies of plant Species classification through feature importance analysis. The most influential features— Vegsout, durflow, semiros, pdias, begflow, wind, leafy, autopoll and insects— uncover the physiological traits underpinning accurate rice classification. This research contributes to advancing rice classification methods and highlights the potential of ANNs in optimizing agricultural practices, ensuring plant safety, and bolstering global trade.

Abstract: Heart attacks, or myocardial infarctions, are a leading cause of mortality worldwide. Early prediction and accurate analysis of potential risk factors play a crucial role in preventing heart attacks and improving patient outcomes. In this study, we conduct a comprehensive review of datasets related to heart attack analysis and prediction. We begin by examining the various types of datasets available for heart attack research, encompassing clinical, demographic, and physiological data. These datasets originate from diverse sources, including hospitals, research institutions, and public health agencies. Our analysis aims to identify common features, data quality, and potential biases in these datasets. Next, we explore the predictive modeling techniques employed in heart attack prediction. Machine learning algorithms, such as decision trees, support vector machines, and deep neural networks, have gained prominence in predicting heart attacks. We discuss the strengths and limitations of these methods and highlight recent advancements in predictive modeling. Furthermore, we delve into the critical risk factors associated with heart attacks. Factors such as age, gender, hypertension, diabetes, and cholesterol levels are examined for their significance in predicting cardiac events. We also investigate the role of lifestyle factors, including smoking, diet, and physical activity, in heart attack risk assessment. Additionally, this review addresses the importance of data preprocessing and feature engineering in improving prediction accuracy. Feature selection methods, missing data handling, and data scaling techniques are discussed to enhance the robustness of heart attack prediction models. In conclusion, this comprehensive dataset review provides valuable insights into the state of heart attack analysis and prediction. It serves as a resource for researchers and healthcare professionals seeking to better understand the datasets available for heart attack research and the methods employed for accurate prediction. Ultimately, our efforts in dataset analysis and predictive modeling contribute to the advancement of preventive cardiology and the reduction of heart attack-related morbidity and mortality.

Abstract: The aim behind analyzing Google Stock Prices dataset is to get a fair idea about the relationships between the multiple attributes a day might have, such as: the opening price for each day, the volume of trading for each day. With over a hundred thousand days of trading data, there are some patterns that can help in predicting the future prices. We proposed an Artificial Neural Network (ANN) model for predicting the closing prices for future days. The prediction is based on these features (date, opening price, highest price, lowest price, volume), which were used as input variables and (closing price) as output variable for our ANN model. Our model was created, trained, and validated using data set in JNN environment, which its title is “Google-Stock-Prices”. The model evaluation showed that the ANN model is able to predict correctly 99.48% of the validation samples.

Abstract: This study has effectively tackled the critical challenge of accurate calorie prediction in dishes by employing a robust neural network-based model. With an outstanding accuracy rate of 99.32% and a remarkably low average error of 0.009, our model has showcased its proficiency in delivering precise calorie estimations. This achievement equips individuals, healthcare practitioners, and the food industry with a powerful tool to promote healthier dietary choices and elevate awareness of nutrition. Furthermore, our in-depth feature importance analysis has shed light on the indispensable role played by specific nutritional attributes in calorie estimation. This unveiling of crucial factors provides valuable insights for further research endeavors and practical applications. Notably, this research extends its impact beyond the immediate context by making substantial contributions to the domains of nutrition science and dietary planning. It underscores the transformative potential of artificial intelligence, demonstrating how it can revolutionize our approach to food, nutrition, and health. As the world grapples with the challenges of diet-related health issues and environmental concerns, the accuracy and precision achieved in calorie prediction through neural networks represent a significant stride towards more informed and conscientious dietary practices. In this era of data-driven decision-making, our research paves the way for healthier lifestyles, heightened nutritional awareness, and a more health-conscious society.

Abstract - The aim of the study is to identify the degree of administrative transparency in the Palestinian higher educational institutions in the Gaza Strip. In the study, the researchers adopted a descriptive and analytical method. The research population consisted of administrative staff, whether academic or administrative, except for those in senior management or the university council. The study population reached 392 employees. A random sample was selected (197). The number of questionnaires recovered was (160) with a recovery rate of (81.2%). The researchers used a questionnaire for the data collection and were treated using SPSS to obtain the results. The results show that there is no significant difference between male responses and female responses due to gender variable. The results also confirm that there is no significant difference between respondents' responses due to the age variable. The results also showed a significant difference between respondents' responses attributed to the university variable. There is a fundamental difference between respondents' responses attributed to the scientifically qualified variable. The results also confirmed a significant difference between respondents' responses attributed to the management level variable. The results also confirmed a significant difference between respondents' responses due to variable years of service. The research reached a number of recommendations, the most important of which is: The necessity of Palestinian universities to adhere to the application of transparency standards in all university activities. The need to benefit from regional and international experience in the application of transparency systems within universities and to examine the possibility of applying these systems in our universities. As well as the need to engage in the program of teaching transparency in universities, as it is confirmed that only five universities participated in this experiment. The importance of raising awareness among the employees of Palestinian universities to clarify the foundations of building transparency and its dimensions to represent the active supporter through workshops and seminars.

Abstract: Forests are areas with a high density of trees, and they play a vital role in the health of the planet. They provide a habitat for a wide variety of plant and animal species, and they help to regulate the climate by absorbing carbon dioxide from the atmosphere. While in 2010, the world had 3.92Gha of forest cover, covering 30% of its land area, in 2019, there was a loss of forest cover of 24.2Mha according to the Global Forest Watch institute. Discovery and classification depend on human experience and effort, so the error in the results of this process can lead to forest fires and disasters. Therefore, deep learning algorithms from artificial intelligence and machine learning sciences have been applied to help specialists avoid false or inaccurate diagnoses when detecting Forest fires in images using a pre-trained convolutional neural network called VGG16. The model was customized to fit the Forest fires classification and then applied to a dataset consisting of (14,000) of the Forests collected from the Kaggle depository. We trained, validated, and tested the modified VGG16 model. The proposed VGG16 model obtained Precision (99.96%), Recall (99.96%), and F1-Score (99.96%).

Abstract: A corn crop typically refers to a large-scale cultivation of corn (also known as maize) for commercial purposes such as food production, animal feed, and industrial uses. Corn is one of the most widely grown crops in the world, and it is a major staple food for many cultures. Corn crops are grown in various regions of the world with different climates, soil types, and farming practices. In the United States, for example, the Midwest is known as the "Corn Belt" due to its extensive corn production. Corn crops can be grown using a variety of methods, including conventional tillage, no-till farming, and the use of genetically modified crops. Due to its importance, there is a need for discovering the corn diseases and treating them. The aim of this study is to propose a deep learning model for the classification of corn leaf diseases based on Convolutional Neural Network. A model for classifying maize diseases was developed using a dataset for classifying Corn diseases that contains 4 classes of disease. The dataset was collected from Keggel website. The proposed model was trained, validated, and tested. The F1-score (99.83%), Recall (99.83%), precision (99.83%), Accuracy (99.83%).

Abstract: Fast food refers to quick, convenient, and ready-to-eat meals that are usually sold at chain restaurants or take-out establishments. Fast food is often criticized for its unhealthy ingredients, such as high levels of salt, sugar, and unhealthy fats, and its contribution to the growing obesity epidemic. Despite this, fast food remains popular due to its affordability, convenience, and widespread availability. Many fast food chains have attempted to respond to these criticisms by offering healthier options, such as salads and grilled chicken sandwiches, and by using more natural and locally sourced ingredients. The aim in this paper to propose a deep learning model for the classification of fast food dishes. The proposed model, Xception, was trained on natural images and was fine-tuned to make up the fast food meals. The researchers collected the Fast Food V2 dataset from Kaggle depository, the dataset, contained 20,000 images. The dataset has ten labels of food images comprised of Baked Potato, Burger, Crispy Chicken, Donut, Fries, Hot Dog, Pizza, Sandwich, Taco, and Taquito. The dataset was split into three sets: training, validation and testing. The accuracy, F1-score, recall, precision on the separate test set showed that classification of fast food was accuracy (95.13%), Precision (95.34%), Recall (95.13%), and F1-Score (95.14%).

Abstract: In this study, we explore the challenge of identifying and preventing diseases in apple trees, which is a popular activity but can be difficult due to the susceptibility of these trees to various diseases. To address this challenge, we propose the use of Convolutional Neural Networks, which have proven effective in automatically detecting plant diseases. To validate our approach, we use images of apple leaves, including Apple Rot Leaves, Leaf Blotch, Healthy Leaves, and Scab Leaves collected from Kaggle which is part from the Plant Village dataset. We generate a comprehensive training dataset using techniques such as image filtering, compression, and generation. Our model achieves impressive accuracy scores for all classes, with an overall accuracy of 99.93% on a dataset of 10,000 labeled images .

Abstract: Context: grapevine leaves are an important agricultural product that is used in many Middle Eastern dishes. The species from which the grapevine leaf originates can differ in terms of both taste and price. Method: In this study, we build a deep learning model to tackle the problem of grape leaf classification. 500 images were used (100 for each species) that were then increased to 10,000 using data augmentation methods. Convolutional Neural Network (CNN) algorithms were applied to build this model specifically using the pre-trained model on top of the VGG16 architecture. Then, dense layers were added to classify the output of the Convolutional layers and classify outputs to the five classes (species) the leaf belonged to. Results: It was found that feature extraction without fine-tuning the convolutional layers yielded poor results, about 86% accuracy, while training the whole network along with some data preprocessing gave the best results, about 99.45% accuracy on the testing dataset. Conclusions: The proposed CNN model is an effective one for the problem of classification of grape leaf species.

Abstract: Tomatoes are among the most popular vegetables in the world due to their frequent use in many dishes, which fall into many varieties in common and traditional foods, and due to their rich ingredients such as vitamins and minerals, so they are frequently used on a daily basis, When we focus our attention on this vegetable, we must also focus and take into consideration the diseases that affect this vegetable, a deep learning model that classifies tomato diseases has been proposed. The aim of this paper is to diagnose tomato diseases based on a dataset containing 11000 picture and 11 classes. The model gave the final accuracy test with Accuracy (99.87%), F1-score (99.87%), Recall (99.87%), and Precision (99.88%) in an estimated time 1.36 second, as with these results it proved its effectiveness and good ability in the classification of the testing data.

Abstract: Lemons are an important fruit that have a wide range of uses and benefits, from culinary to health to household and beauty applications. Deep learning techniques have shown promising results in image classification tasks, including fruit quality detection. In this paper, we propose a convolutional neural network (CNN)-based approach for detecting the quality of lemons by analysing visual features such as colour and texture. The study aims to develop and train a deep learning model to classify lemons based on their quality, evaluate the model's performance, compare it to traditional machine learning approaches, and identify key factors that affect the model's performance. The dataset used in the study consists of approximately 2533 images of lemons and an empty surface, divided into training, test, and validation data, and includes images of both good and bad quality lemons under different lighting conditions. The deep learning model achieved an accuracy of 99.74% on the test dataset and outperformed traditional machine learning approaches. The developed model has the potential to improve efficiency and accuracy in lemon quality control in the agriculture and food industry.

Abstract: Vegetables are an essential component of a healthy diet and play a critical role in promoting overall health and well- being. Vegetables are rich in important vitamins and minerals, including vitamin C, folate, potassium, and iron. They also provide fiber, which helps maintain digestive health and prevent chronic diseases. We are proposing a deep learning model for the classification of vegetables. A dataset was collected from Kaggle depository for Vegetable with 15000 images for 15 different classes. The data was preprocessed, normalized and split into three sets (train, valid, test). The proposed model was trained and validated using the train and valid sets and accuracy of both training and validation was very high. For the evaluation of the proposed model we utilized these metrics: accuracy, F1-score, precision, Recall and time required for testing. We then tested the proposed model using the test set. The result of the testing was accuracy (99.95%), F1-score (99.95%), precision (99.95%), Recall (99.95%) and time required for testing the test set was 1.38 seconds.

Abstract: Classifying sea animals is an important problem in marine biology and ecology as it enables the accurate identification and monitoring of species populations, which is crucial for understanding and protecting marine ecosystems. This paper addresses the problem of classifying 19 different sea animals using convolutional neural networks (CNNs). The proposed solution is to use a pretrained MobileNetV2 model, which is a lightweight and efficient CNN architecture, and fine-tune it on a dataset of sea animals. The results of the study show that the fine-tuned MobileNetV2 model is able to achieve an accuracy of 85% on the classification task, which is competitive with the state-of-the-art methods. Additionally, the study also found that data augmentation and regularization techniques such as dropout were important for preventing overfitting and improving the performance of the model. This study demonstrates the potential of using pretrained models and efficient CNN architectures for classifying sea animals, and it provides insights into the challenges and best practices for solving this important problem in marine biology and ecology.

Abstract: Pistachio nuts are a valuable source of nutrition and are widely cultivated for commercial purposes. The accurate classification of different pistachio varieties is important for quality control and market analysis. In this study, we propose a new model for the classification of different pistachio varieties using Convolutional Neural Networks (CNNs). We collected a dataset of pistachio images form Kaggle depository with two varieties (Kirmizi and Siirt). The images were then preprocessed and used to train a CNN model based on VGG16. We evaluated the performance of the VGG16 on a held-out test set. Our results show that the CNN-based model VGG16 performed very well in terms of accuracy and efficiency. The VGG16 model was able to accurately classify different pistachio varieties with an accuracy of over 99.91%. Additionally, the VGG16 was able to generalize well to new and unseen data, demonstrating its ability to handle variability in the pistachio images. This study highlights the potential of CNNs for the classification of different pistachio varieties, and has important implications for the pistachio industry. The results suggest that this approach can be used to improve the quality control process and enhance market analysis.

Abstract: In recent years, the outbreak of various poultry diseases has posed a significant threat to the global poultry industry. Therefore, the accurate and timely detection of chicken diseases is critical to reduce economic losses and prevent the spread of diseases. In this study, we propose a method for classifying chicken diseases using a convolutional neural network (CNN). The proposed method involves preprocessing the chicken images, building and training a CNN model, and evaluating the performance of the model. The dataset used in this study comprises chicken images of three different diseases: Newcastle disease, avian influenza, and infectious bursal disease. The proposed method achieved an overall F1-score of 99.04% in classifying the chicken diseases. The results demonstrate the effectiveness of using CNN in classifying chicken diseases and provide a promising approach for early detection and diagnosis of poultry diseases.