Search

Copyright of Journal of Kirkuk University for Agricultural Sciences is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Kirkuk University for Agricultural Sciences is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Urban air mobility, also known as UAM, is currently being researched in a variety of metropolitan regions throughout the world as a potential new mode of transport for travelling shorter distances inside a territory. In this article, we investigate whether or not the market can back the necessary financial commitments to deploy UAM. A challenge in defining and addressing a critical phase of such guidance is called a demand forecast problem. To achieve this goal, a deep learning model for forecasting temporal data is proposed. This model is used to find and study the scientific issues involved. A benchmark dataset of 150,000 records was used for this purpose. Our experiments used different state-of-the-art DL models: LSTM, GRU, and Transformer for UAM demand prediction. The transformer showed a high performance with an RMSE of 0.64, allowing decision-makers to analyze the feasibility and viability of their investments. [ABSTRACT FROM AUTHOR]

Forecasting rainfall is crucial to the well-being of individuals and is significant everywhere in the world. It contributes to reducing the disastrous effects of floods on agriculture, human life, and socioeconomic systems. This study discusses the challenges of effectively forecasting rainfall and floods and the necessity of combining data with flood channel mathematical modelling to forecast floodwater levels and velocities. This research focuses on leveraging historical meteorological data to find trends using machine learning and deep learning approaches to estimate rainfall. The Bangladesh Meteorological Department provided the data for the study, which also uses eight machine learning algorithms. The performance of the machine learning models is examined using evaluation measures like the R2 score, root mean squared error and validation loss. According to this research's findings, polynomial regression, random forest regression, and long short-term memory (LSTM) had the highest performance levels. Random forest and polynomial regression have an R2 value of 0.76, while LSTM has a loss value of 0.09, respectively. [ABSTRACT FROM AUTHOR]

Apple foliar diseases are a group of diseases that affect the leaves of apple trees. These diseases can significantly impact apple tree health and fruit yield. Ordinary apple foliar diseases include frog_eye_leaf_spots, powdery mildew, rust, apple scabs, etc. Early detection of these diseases is important for effective apple crop management to increase the yield of apples. Therefore, this research proposes a fine-tuned EfficientNetB3 model for the quick and precise assessment of these apple foliar diseases. A dataset containing 23,187 RGB images of eleven different apple foliar diseases is used for experimentation. The proposed model is compared with four transfer learning models, i.e., InceptionResNetV2, ResNet50, AlexNet, and VGG16. All models are fine-tuned by adding different layers like the global average pooling layer, flatten layer, dropout layer, and dense layer. The performance of these five models is compared in terms of the precision, recall, accuracy, and F1-score. The EfficientNetB3 outperformed the other models in terms of all performance parameters. The best model is further optimized with the help of three optimizers, i.e., Adam, SGD, and Adagrad. The proposed model achieved the precision, recall, and F1-score values of 86%, 88%, and 86%, respectively, at 32 batch sizes and 10 epochs. This research formulated a model for an apple foliar disease diagnosis within sustainable agriculture. [ABSTRACT FROM AUTHOR]

The use of offensive terms in user-generated content on different social media platforms is one of the major concerns for these platforms. The offensive terms have a negative impact on individuals, which may lead towards the degradation of societal and civilized manners. The immense amount of content generated at a higher speed makes it humanly impossible to categorise and detect offensive terms. Besides, it is an open challenge for natural language processing (NLP) to detect such terminologies automatically. Substantial efforts are made for high-resource languages such as English. However, it becomes more challenging when dealing with resource-poor languages such as Urdu. Because of the lack of standard datasets and pre-processing tools for automatic offensive terms detection. This paper introduces a combinatorial preprocessing approach in developing a classification model for cross-platform (Twitter and YouTube) use. The approach uses datasets from two different platforms (Twitter and YouTube) the training and testing the model, which is trained to apply decision tree, random forest and naive Bayes algorithms. The proposed combinatorial pre-processing approach is applied to check how machine learning models behave with different combinations of standard pre-processing techniques for low-resource language in the cross-platform setting. The experimental results represent the effectiveness of the machine learning model over different subsets of traditional pre-processing approaches in building a classification model for automatic offensive terms detection for a low resource language, i.e., Urdu, in the cross-platform scenario. In the experiments, when dataset D1 is used for training and D2 is applied for testing, the pre-processing approach named Stopword removal produced better results with an accuracy of 83.27%. Whilst, in this case, when dataset D2 is used for training and D1 is applied for testing, stopword removal and punctuation removal were observed as a better preprocessing approach with an accuracy of 74.54%. The combinatorial approach proposed in this paper outperformed the benchmark for the considered datasets using classical as well as ensemble machine learning with an accuracy of 82.9% and 97.2% for dataset D1 and D2, respectively. [ABSTRACT FROM AUTHOR]

Thalassemia syndrome is a genetic blood disorder induced by the reduction of normal hemoglobin production, resulting in a drop in the size of red blood cells. In severe forms, it can lead to death. This genetic disorder has posed a major burden on public health wherein patients with severe thalassemia need periodic therapy of iron chelation and blood transfusion for survival. Therefore, controlling thalassemia is extremely important and is made by promoting screening to the general population, particularly among thalassemia carriers. Today Twitter is one of the most influential social media platforms for sharing opinions and discussing different topics like people’s health conditions and major public health affairs. Exploring individuals’ sentiments in these tweets helps the research centers to formulate strategies to promote thalassemia screening to the public. An effective Lexiconbased approach has been introduced in this study by highlighting a classifier called valence aware dictionary for sentiment reasoning (VADER). In this study applied twitter intelligence tool (TWINT), Natural Language Toolkit (NLTK), and VADER constitute the three main tools. VADER represents a gold-standard sentiment lexicon, which is basically tailored to attitudes that are communicated by using social media. The contribution of this study is to introduce an effective Lexicon-based approach by highlighting a classifier called VADER to analyze the sentiment of the general population, particularly among thalassemia carriers on the social media platform Twitter. In this study, the results showed that the proposed approach achieved 0.829, 0.816, and 0.818 regarding precision, recall, together with F-score, respectively. The tweets were crawled using the search keywords, “thalassemia screening,” thalassemia test, “and thalassemia diagnosis”. Finally, results showed that India and Pakistan ranked the highest in mentions in tweets by the public’s conversations on thalassemia screening with 181 and 164 tweets, respectively. [ABSTRACT FROM AUTHOR]

A vehicular ad hoc network (VANET) is a technique that uses vehicles with the ability to sense data from the environment and use it for their safety measures. Flooding is a commonly used term used for sending network packets. VANET may cause redundancy, delay, collision, and the incorrect receipt of the messages to their destination. Weather information is one of the most important types of information used for network control and provides an enhanced version of the network simulation environments. The network traffic delay and packet losses are the main problems identified inside the network. In this research, we propose a routing protocol which can transmit the weather forecasting information on demand based on source vehicle to destination vehicles, with the minimum number of hop counts, and provide significant control over network performance parameters. We propose a BBSF-based routing approach. The proposed technique effectively enhances the routing information and provides the secure and reliable service delivery of the network performance. The results taken from the network are based on hop count, network latency, network overhead, and packet delivery ratio. The results effectively show that the proposed technique is reliable in reducing the network latency, and that the hop count is minimized when transferring the weather information. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Kirkuk University for Agricultural Sciences is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Monitoring the Earth's surface and objects is important for many applications, such as managing natural resources, crop yield predictions, and natural hazard analysis. Remote sensing is one of the most efficient and cost-effective solutions for analyzing land-use and land-cover (LULC) changes over the Earth's surface through advanced computer algorithms, such as classification and change detection. In the past literature, various developments were made to change detection algorithms to detect LULC multitemporal changes using optical or microwave imagery. The optical-based hyperspectral highlights the critical information, but sometimes it is difficult to analyze the dataset due to the presence of atmospheric distortion, radiometric errors, and misregistration. In this work, an artificial neural network-based post-classification comparison (ANPC) as change detection has been utilized to detect the muti-temporal LULC changes over a part of Uttar Pradesh, India, using the Hyperion EO-1 dataset. The experimental outcomes confirmed the effectiveness of ANPC (92.6%) as compared to the existing models, such as a spectral angle mapper (SAM) based post-classification comparison (SAMPC) (89.7%) and k-nearest neighbor (KNN) based post-classification comparison (KNNPC) (91.2%). The study will be beneficial in extracting critical information about the Earth's surface, analysis of crop diseases, crop diversity, agriculture, weather forecasting, and forest monitoring. [ABSTRACT FROM AUTHOR]

Throughout the use of the small battery-operated sensor nodes encourage us to develop an energy-efficient routing protocol for wireless sensor networks (WSNs). The development of an energy-efficient routing protocol is a mainly adopted technique to enhance the lifetime of WSN. Many routing protocols are available, but the issue is still alive. Clustering is one of the most important techniques in the existing routing protocols. In the clustering-based model, the important thing is the selection of the cluster heads. In this paper, we have proposed a scheme that uses the bubble sort algorithm for cluster head selection by considering the remaining energy and the distance of the nodes in each cluster. Initially, the bubble sort algorithm chose the two nodes with the maximum remaining energy in the cluster and chose a cluster head with a small distance. The proposed scheme performs hierarchal routing and direct routing with some energy thresholds. The simulation will be performed in MATLAB to justify its performance and results and compared with the ECHERP model to justify its performance. Moreover, the simulations will be performed in two scenarios, gateway-based and without gateway to achieve more energy-efficient results. [ABSTRACT FROM AUTHOR]

The amount of data captured is expanding day by day which leads to the need for a monitoring system that helps in decision making. Current technologies such as cloud, machine learning (ML) and Internet of Things (IoT) provide a better solution for monitoring automation systems efficiently. In this paper, a prediction model that monitors real-time data of sensor nodes in a clinical environment using a machine learning algorithm is proposed. An IoT-based smart hospital environment has been developed that controls and monitors appliances over the Internet using different sensors such as current sensors, a temperature and humidity sensor, air quality sensor, ultrasonic sensor and flame sensor. The IoT-generated sensor data have three important characteristics, namely, real-time, structured and enormous amount. The main purpose of this research is to predict early faults in an IoT environment in order to ensure the integrity, accuracy, reliability and fidelity of IoT-enabled devices. The proposed fault prediction model was evaluated via decision tree, K-nearest neighbor, Gaussian naive Bayes and random forest techniques, but random forest showed the best accuracy over others on the provided dataset. The results proved that the ML techniques applied over IoT-based sensors are well efficient to monitor this hospital automation process, and random forest was considered the best with the highest accuracy of 94.25%. The proposed model could be helpful for the user to make a decision regarding the recommended solution and control unanticipated losses generated due to faults during the automation process. [ABSTRACT FROM AUTHOR]

Sentiment analysis taskhas widely been studied for various languages such as English and French. However, Roman Urdu sentiment analysis yet requires more attention from peer-researchers due to the lack of Off-the-Shelf Natural Language Processing (NLP) solutions. The primary objective of this study is to investigate the diverse machine learning methods for the sentiment analysis of Roman Urdu data which is very informal in nature and needs to be lexically normalized. To mitigate this challenge, we propose a fine-tuned Support Vector Machine (SVM) powered by Roman Urdu Stemmer. In our proposed scheme, the corpus data is initially cleaned to remove the anomalies from the text. After initial pre-processing, each user review is being stemmed. The input text is transformed into a feature vector using the bag-of-word model. Subsequently, the SVM is used to classify and detect user sentiment. Our proposed scheme is based on a dictionary based Roman Urdu stemmer. The creation of the Roman Urdu stemmer is aimed at standardizing the text so as to minimize the level of complexity. The efficacy of our proposed model is also empirically evaluated with diverse experimental configurations, so as to fine-tune the hyper-parameters and achieve superior performance. Moreover, a series of experiments are conducted on diverse machine learning and deep learning models to compare the performance with our proposed model. We also introduced the largest dataset on Roman Urdu, i.e., Roman Urdu e-commerce dataset (RUECD), which contains 26K+ user reviews annotated by the group of experts. The RUECD is challenging and the largest dataset available of Roman Urdu. The experiments show that the newly generated dataset is quite challenging and requires more attention from the peer researchers for Roman Urdu sentiment analysis. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSN) deploy many nodes over an extended area for traffic surveillance, environmental monitoring, healthcare, tracking wildlife, and military sensing. Nodes of the WSN have a limited amount of energy. Each sensor node collects information from the surrounding area and forwards it onto the cluster head, which then sends it on to the base station (BS). WSNs extend the lifetime of the network through clustering techniques. Choosing nodes with the greatest residual energy as cluster heads is based on the idea that energy consumption is periodically distributed between nodes. The sink node gathers information from its environment that is then transmitted to the base station. The clustering protocol uses a considerably amount of energy for data collection and transmission, with additional energy used for listening to the nodes. It also contributes to channel sensing and avoiding collisions alongside energy transmission. Most clustering techniques do not consider cluster fails, because of which detection through cluster heads or the BS is not possible. Terminated nodes and sub-cluster heads thus continue to transmit information to the failed sub-cluster head, which leads to higher energy consumption. In light of this, we propose a technique to choose cluster heads while reducing the use of CSMA/CA through fault tolerance to determine the failure of the cluster heads by consuming little energy. This work here contributes to increasing the life of the WSN and conserving its energy by more than a half-sensor node per round. [ABSTRACT FROM AUTHOR]

Deep learning techniques, particularly convolutional neural networks (CNNs), have exhibited remarkable performance in solving vision-related problems, especially in unpredictable, dynamic, and challenging environments. In autonomous vehicles, imitation-learning-based steering angle prediction is viable due to the visual imagery comprehension of CNNs. In this regard, globally, researchers are currently focusing on the architectural design and optimization of the hyperparameters of CNNs to achieve the best results. Literature has proven the superiority of metaheuristic algorithms over the manual-tuning of CNNs. However, to the best of our knowledge, these techniques are yet to be applied to address the problem of imitation-learning-based steering angle prediction. Thus, in this study, we examine the application of the bat algorithm and particle swarm optimization algorithm for the optimization of the CNN model and its hyperparameters, which are employed to solve the steering angle prediction problem. To validate the performance of each hyperparameters' set and architectural parameters' set, we utilized the Udacity steering angle dataset and obtained the best results at the following hyperparameter set: optimizer, Adagrad; learning rate, 0.0052; and nonlinear activation function, exponential linear unit. As per our findings, we determined that the deep learning models show better results but require more training epochs and time as compared to shallower ones. Results show the superiority of our approach in optimizing CNNs through metaheuristic algorithms as compared with the manual-tuning approach. Infield testing was also performed using the model trained with the optimal architecture, which we developed using our approach. [ABSTRACT FROM AUTHOR]

The software design model performs an important role in modern software engineering methods. Especially in Model-Driven Engineering (MDE), it is treated as an essential asset of software development; even programming language code is produced by the models. If the model has errors, then they can propagate into the code. Model verification tools check the presence of errors in the model. This paper shows how a UML class model verification tool has been built to support complex models and unsupported elements such as XOR constraints and dependency relationships. This tool uses ontology for verifying the UML class model. It takes a class model in XMI format and generates the OWL file. Performs verification of model in two steps: (1) uses the ontology-based algorithm to verify association multiplicity constraints; and (2) uses ontology reasoner for the verification of XOR constraints and dependency relationships. The results show the proposed tool improves the verification efficiency and supports the verification of UML class model elements that have not been supported by any existing tool. [ABSTRACT FROM AUTHOR]

Wireless sensor networks are known for their monitoring and tracking application-specific operations. These operations diversely demand improvement in existing strategies and their parameters. One key parameter is energy usage during operations. Energy plays a vital role in each application, as the wireless sensor networks lack battery lifetime and energy resources. So, there is a need for an optimized and efficient routing method with regard to energy consumption in wireless sensor networks. For multi-hop routing, the genetic algorithm serves as a robust algorithm with diverse optimized routing plans to improve the lifespan for large-scale wireless sensor networks. In this paper, the genetic algorithm provides the optimized routes for data operations and improves the lifetime of wireless sensor networks by saving energy. The performance of the genetic algorithm is compared with the TEEN algorithm. [ABSTRACT FROM AUTHOR]

High-dimensional medical data makes prediction a complex and difficult task. This study aims at modeling predictive models for medical data. Two datasets of medical data are applied in the study — one online available dataset (Heart Disease data) and another real clinical dataset (Eye Infection Data). A wide range of machine learning algorithms are applied in the modeling stage: Decision Tree, Multilayer Perceptron, Naive Bayesian, Random Forest, and Support Vector Machine. Furthermore, bagging and voting ensemble methods have also been applied with base learners. Both split and cross-validation methods are adopted for the model validation, and well-established evaluation metrics such as accuracy, precision, recall, and F-measure have been considered as evaluation metrics for the predictive models. The method applied for the modeling is comprised of two stages. The first stage uses available features for the predictions. In the second stage, selected features based on positive correlation are used. The adopted method is also for deep learning, especially Convolutional Neural Network (CNN) is applied to analyze the outcomes compared to conventional machine learning algorithms. The experimental results reveal that better predictions are achieved in the second stage. Besides, experiments also indicate split percentage produces better predictive models, and marginally better outcomes are observed in the presence of ensemble methods in comparison with base models. NB outperformed other algorithms with the highest accuracy rate as 88.90%, and MLP obtained 97.50% accuracy for Heart Disease and Eye Infection data, respectively, using 80–20 splits in the second stage. However, the CNN model performed poorly due to the size of the considered datasets. • Two medical datasets are applied in the study: one online available and the other real. • Machine learning algorithms including DT, MLP, NB and RF are applied in the modeling. • The method applied for the modeling is comprised of two stages. • The experimental results reveal that better predictions are achieved in the second stage. • NB outperformed for an online dataset with 88.90% accuracy and MLP with 97.50% for real dataset. [ABSTRACT FROM AUTHOR]

Research on faculty engagement in computer science and e-learning environments is limited. Students in computer science majors and courses often cite the lack of engagement of their faculty as a reason for their decision to switch majors, drop out or perform poorly. With the shift to e-learning associated with the current global pandemic, reports of faculty engagement across countries and higher education systems converged to indicate a reduced level of interactivity. Using a cross-sectional sample of 39 lecturers and professors from a southern public university in Saudi Arabia, this manuscript documents empirically the low levels of computer science faculty engagement during the 2020 spring semester (March–May). The study found support for the hypotheses linking higher levels of empathetic instruction, an exhibition of exemplary performance traits, utilization of community building strategies and use of storytelling and students' engagement. The study also found that many faculties need immediate and significant training on making their online instruction more interactive and exciting. Theoretically, the evidence presented confirms the importance of faculty engagement as the main predictor of desirable students' outcomes across e-learning, as well as computer science learning environments. [ABSTRACT FROM AUTHOR]