Search

Pap smear screening test is one of the early prevention efforts to detect cervical cancer. Manual screening tests are still prone to observation errors. This study aims to create a convolutional neural network (CNN) model and support vector machine (SVM) model to identify cervical cancer through pap smear images. The data used are 4049 normal and pathological cervical cells in pap smear images sourced from SIPaKMeD, which were divided into 5 classes based on the level of cancer malignancy. The CNN model is used to extract features on the pap smear image, and SVM is used to carry out the classification. The results of this study are four cervical cancer classification models on pap smear images using Resnet50 and Resnet50V2 architecture and SVM algorithms with different scenarios on freeze and unfreeze of the convolution layer. The classification model with the best performance has an accuracy of 97.09. CNN model with freezing the convolution layer provides much faster in the pre-trained model and the integration of this model with the SVM as the classifier results in the classification model of cervical cells in pap smear images with high accuracy. © 2024, Semarak Ilmu Publishing. All rights reserved. more...

Pap smear screening test is one of the early prevention efforts to detect cervical cancer. Manual screening tests are still prone to observation errors. This study aims to create a convolutional neural network (CNN) model and support vector machine (SVM) model to identify cervical cancer through pap smear images. The data used are 4049 normal and pathological cervical cells in pap smear images sourced from SIPaKMeD, which were divided into 5 classes based on the level of cancer malignancy. The CNN model is used to extract features on the pap smear image, and SVM is used to carry out the classification. The results of this study are four cervical cancer classification models on pap smear images using Resnet50 and Resnet50V2 architecture and SVM algorithms with different scenarios on freeze and unfreeze of the convolution layer. The classification model with the best performance has an accuracy of 97.09. CNN model with freezing the convolution layer provides much faster in the pre-trained model and the integration of this model with the SVM as the classifier results in the classification model of cervical cells in pap smear images with high accuracy. © 2024, Semarak Ilmu Publishing. All rights reserved. more...

The development of a decision support system (DSS) called the Risk Management System aims to empower farmers in making well-informed decisions, ultimately enhancing rice field production. This system focuses on providing a monitoring mechanism that optimizes monitoring and control efforts in paddy plantations. By employing predictive modeling, integrated pest monitoring, and decision support systems for pests, weeds, abiotic variables, and rainfall patterns, it predicts the likelihood and consequences of potential weed infestations, pest outbreaks, and changes in weather patterns like temperature and rainfall. By leveraging precision agriculture technologies and data-driven insights, the Risk Management System keeps a vigilant watch on disease and pest presence in paddy fields. It promptly alerts farmers when specific thresholds are surpassed, enabling them to take immediate action. The system facilitates effective data analysis for extension officers, enabling them to swiftly respond to emergency situations. Overall, this method offers a practical and efficient response to the challenges faced by paddy farmers. It equips them with the ability to make informed decisions, increase production, and effectively manage diseases and pests, ultimately leading to improved agricultural outcomes. more...

Worldwide, 422 million people suffer from diabetic disease, and 1.5 million die yearly. Diabetes is a threat to people who still fail to cure or maintain it, so it is challenging to predict this disease accurately. The existing systems face data over-fitting issues, convergence problems, non-converging optimization complex predictions, and latent and predominant feature extraction. These issues affect the system's performance and reduce diabetic disease detection accuracy. Hence, the research objective is to create an improved diabetic disease detection system using a Flock Optimization Algorithm-Based Deep Learning Model (FOADLM) feature modeling approach that leverages the PIMA Indian dataset to predict and classify diabetic disease cases. The collected data is processed by a Gaussian filtering approach that eliminates irrelevant information, reducing the overfitting issues. Then flock optimization algorithm is applied to detect the sequence; this process is used to reduce the convergence and optimization problems. Finally, the recurrent neural approach is applied to classify the normal and abnormal features. The entire research implementation result is carried out with the help of the MATLAB program and the results are analyzed with accuracy, precision, recall, computational time, reliability scalability, and error rate measures like root mean square error, mean square error, and correlation coefficients. In conclusion, the system evaluation result produced 99.23 accuracy in predicting diabetic disease with the metrics. more...

Worldwide, 422 million people suffer from diabetic disease, and 1.5 million die yearly. Diabetes is a threat to people who still fail to cure or maintain it, so it is challenging to predict this disease accurately. The existing systems face data over-fitting issues, convergence problems, non-converging optimization complex predictions, and latent and predominant feature extraction. These issues affect the system's performance and reduce diabetic disease detection accuracy. Hence, the research objective is to create an improved diabetic disease detection system using a Flock Optimization Algorithm-Based Deep Learning Model (FOADLM) feature modeling approach that leverages the PIMA Indian dataset to predict and classify diabetic disease cases. The collected data is processed by a Gaussian filtering approach that eliminates irrelevant information, reducing the overfitting issues. Then flock optimization algorithm is applied to detect the sequence; this process is used to reduce the convergence and optimization problems. Finally, the recurrent neural approach is applied to classify the normal and abnormal features. The entire research implementation result is carried out with the help of the MATLAB program and the results are analyzed with accuracy, precision, recall, computational time, reliability scalability, and error rate measures like root mean square error, mean square error, and correlation coefficients. In conclusion, the system evaluation result produced 99.23 accuracy in predicting diabetic disease with the metrics. more...

The development of a decision support system (DSS) called the Risk Management System aims to empower farmers in making well-informed decisions, ultimately enhancing rice field production. This system focuses on providing a monitoring mechanism that optimizes monitoring and control efforts in paddy plantations. By employing predictive modeling, integrated pest monitoring, and decision support systems for pests, weeds, abiotic variables, and rainfall patterns, it predicts the likelihood and consequences of potential weed infestations, pest outbreaks, and changes in weather patterns like temperature and rainfall. By leveraging precision agriculture technologies and data-driven insights, the Risk Management System keeps a vigilant watch on disease and pest presence in paddy fields. It promptly alerts farmers when specific thresholds are surpassed, enabling them to take immediate action. The system facilitates effective data analysis for extension officers, enabling them to swiftly respond to emergency situations. Overall, this method offers a practical and efficient response to the challenges faced by paddy farmers. It equips them with the ability to make informed decisions, increase production, and effectively manage diseases and pests, ultimately leading to improved agricultural outcomes. more...

As Massive Open Online Courses (MOOCs) expand and diversify, more and more researchers study recommender systems that take advantage of interaction data to keep students interested and boost their performance. In a typical roadmap, courses and videos are recommended using a graph model, but this does not take into account the user’s learning needs with some particular subjects. However, all existing graph models degrade performances either by ignoring the data sparsity issue caused by a large number of concepts, which may lead to biased recommendations, or by constructing improper contrasting pairs, which may result in graph noise. To overcome both challenges, we propose a gRaph cOntrastive Multi-view framEwork (ROME) from hyperbolic angular space to learn user and concept representations based on user-user and concept-concept relationships. The first step is to use hyperbolic and Euclidean space representations as different views of graph and maximize the mutual information between them. Furthermore, we maximize the angular decision margin in graph contrastive training objects to enhance pairwise discriminative power. Our experiments on a large-scale real-world MOOC dataset show that the proposed approach outperforms several baselines and state-of-the-art methods for predicting and recommending concepts of interest to users. more...

As Massive Open Online Courses (MOOCs) expand and diversify, more and more researchers study recommender systems that take advantage of interaction data to keep students interested and boost their performance. In a typical roadmap, courses and videos are recommended using a graph model, but this does not take into account the user’s learning needs with some particular subjects. However, all existing graph models degrade performances either by ignoring the data sparsity issue caused by a large number of concepts, which may lead to biased recommendations, or by constructing improper contrasting pairs, which may result in graph noise. To overcome both challenges, we propose a gRaph cOntrastive Multi-view framEwork (ROME) from hyperbolic angular space to learn user and concept representations based on user-user and concept-concept relationships. The first step is to use hyperbolic and Euclidean space representations as different views of graph and maximize the mutual information between them. Furthermore, we maximize the angular decision margin in graph contrastive training objects to enhance pairwise discriminative power. Our experiments on a large-scale real-world MOOC dataset show that the proposed approach outperforms several baselines and state-of-the-art methods for predicting and recommending concepts of interest to users. more...

Brain tumor classification is important for diagnosing and treating cancers. Deep Learning has improved medical imaging with Artificial Intelligence (AI). Brain tumor's shape, size, and intensity make subclassification difficult. Medical imaging data is scarce. Any medical data involves privacy of the patients, hence unlike other image data, medical image data is not easily available. There are only few medical image data that is freely available for researchers. This project aims to develop a deep transfer learning model that can accurately classify brain cancers utilizing limited Medical Resonance Images (MRI) images. To achieve the goal, a modified GoogleNet model was used. Various learning algorithms were tested. The experiment also examined transfer learning and data augmentation. Finally, F1-average and confusion matrix were used to evaluate the model. Our model outperformed the state-of-the-art model in various research articles, according to performance matrices. Experimenters employed data augmentation and learning algorithms. more...

Brain tumor classification is important for diagnosing and treating cancers. Deep Learning has improved medical imaging with Artificial Intelligence (AI). Brain tumor's shape, size, and intensity make subclassification difficult. Medical imaging data is scarce. Any medical data involves privacy of the patients, hence unlike other image data, medical image data is not easily available. There are only few medical image data that is freely available for researchers. This project aims to develop a deep transfer learning model that can accurately classify brain cancers utilizing limited Medical Resonance Images (MRI) images. To achieve the goal, a modified GoogleNet model was used. Various learning algorithms were tested. The experiment also examined transfer learning and data augmentation. Finally, F1-average and confusion matrix were used to evaluate the model. Our model outperformed the state-of-the-art model in various research articles, according to performance matrices. Experimenters employed data augmentation and learning algorithms. more...

Mental health has long been considered a difficult subject to discuss openly, and stigmas still surround it. Poor mental health has become a prevalent issue since people have difficulty talking about and expressing their feelings. The problem has been escalating during this COVID-19 outbreak. In today's modern society, it is demonstrated that the technology has the capability of assisting health care providers in assisting their patients with mental health concerns. With this idea, a system named EMOICE, which is a speech emotion recognition system to aid mental health issues, is developed. Doctors or therapists can utilize this technique to analyze and comprehend their patients' emotions, which will aid them in making diagnoses. EMOICE can also be used for emotional learning, where people can use empathy and understanding to deal with mental health concerns. EMOICE will use human speech to extract features such as pitch, voice quality, and voice spectral, which will be used by the algorithm to learn and produce accurate results. EMOICE will employ machine learning techniques, and among the classifiers tested and compared, 1D-Convolutional Neural Network (1D-CNN) has a high accuracy value of 94.78 percent. As a result, this approach can help doctors and therapists better understand their patients' thoughts and emotions, as well as help patients become more self-aware and develop empathy for others in their community and the world around them. more...

Bagworm is the most important insect defoliator of oil palm. The bagworm larvae scrape off the leaflets’ epidermis while the older larvae chew the leaflets and leaving multiple holes and causes the palm to lose its photosynthetic capability. A bagworm census should be carried out quickly to determine the extent of damage. However, the conventional practices are heavily dependent on in-situ data collection, which is destructive, less efficient, laborious, and costly. Recently, many studies have incorporated machine learning analysis such as artificial neural network (ANN) in agricultural fields especially in the development of pest prediction model. Therefore, this study was conducted to develop a weather-based bagworm prediction model using ANN-Feature Selection method. Bagworm censuses were done by identifying Metisa plana’s larval stage 1 (L1) to 7 (L7) from 13 random palms by cutting off frond number 17 biweekly and weather data was recorded by installing weather station in an oil palm plantation belongs to TH Plantation Berhad in Muadzam Shah, Pahang, Malaysia from July 2016 to June 2017. The results revealed that the significant weather parameters were frequent at time-lag 12. All the larval stage prediction models from ANN-Feature Selection were able to produce satisfactory R2 values ranging from 0.526 to 0.995. The best model was the L1 model with R2 value of 0.985 and the accuracy of more than 90%. more...

Mental health has long been considered a difficult subject to discuss openly, and stigmas still surround it. Poor mental health has become a prevalent issue since people have difficulty talking about and expressing their feelings. The problem has been escalating during this COVID-19 outbreak. In today's modern society, it is demonstrated that the technology has the capability of assisting health care providers in assisting their patients with mental health concerns. With this idea, a system named EMOICE, which is a speech emotion recognition system to aid mental health issues, is developed. Doctors or therapists can utilize this technique to analyze and comprehend their patients' emotions, which will aid them in making diagnoses. EMOICE can also be used for emotional learning, where people can use empathy and understanding to deal with mental health concerns. EMOICE will use human speech to extract features such as pitch, voice quality, and voice spectral, which will be used by the algorithm to learn and produce accurate results. EMOICE will employ machine learning techniques, and among the classifiers tested and compared, 1D-Convolutional Neural Network (1D-CNN) has a high accuracy value of 94.78 percent. As a result, this approach can help doctors and therapists better understand their patients' thoughts and emotions, as well as help patients become more self-aware and develop empathy for others in their community and the world around them. more...

Bagworm is the most important insect defoliator of oil palm. The bagworm larvae scrape off the leaflets’ epidermis while the older larvae chew the leaflets and leaving multiple holes and causes the palm to lose its photosynthetic capability. A bagworm census should be carried out quickly to determine the extent of damage. However, the conventional practices are heavily dependent on in-situ data collection, which is destructive, less efficient, laborious, and costly. Recently, many studies have incorporated machine learning analysis such as artificial neural network (ANN) in agricultural fields especially in the development of pest prediction model. Therefore, this study was conducted to develop a weather-based bagworm prediction model using ANN-Feature Selection method. Bagworm censuses were done by identifying Metisa plana’s larval stage 1 (L1) to 7 (L7) from 13 random palms by cutting off frond number 17 biweekly and weather data was recorded by installing weather station in an oil palm plantation belongs to TH Plantation Berhad in Muadzam Shah, Pahang, Malaysia from July 2016 to June 2017. The results revealed that the significant weather parameters were frequent at time-lag 12. All the larval stage prediction models from ANN-Feature Selection were able to produce satisfactory R2 values ranging from 0.526 to 0.995. The best model was the L1 model with R2 value of 0.985 and the accuracy of more than 90%. more...

Harmony search algorithm (HSA) is relatively considered as one of the most recent metaheuristic algorithms. HSA is a modern - nature algorithm that simulates the musicians’ natural process of musical improvisation to enhance their instrument’s note to find a state of pleasant (harmony) according to aesthetic standards. Lots of variants of HSA have been suggested to tackle combinatorial optimization problems. They range from hybridizing some components of other metaheuristic approaches (to improve the HSA) to taking some concepts of HSA and utilizing them to improve other metaheuristic methods. This stud y reviews research pertaining to parameter settings of HSA and its applications to efficiently solve hard combinatorial optimization problems. more...

Harmony search algorithm (HSA) is relatively considered as one of the most recent metaheuristic algorithms. HSA is a modern - nature algorithm that simulates the musicians’ natural process of musical improvisation to enhance their instrument’s note to find a state of pleasant (harmony) according to aesthetic standards. Lots of variants of HSA have been suggested to tackle combinatorial optimization problems. They range from hybridizing some components of other metaheuristic approaches (to improve the HSA) to taking some concepts of HSA and utilizing them to improve other metaheuristic methods. This stud y reviews research pertaining to parameter settings of HSA and its applications to efficiently solve hard combinatorial optimization problems. more...

Limited approaches have been applied to Arabic sentiment analysis for a five-point classification problem. These approaches are based on single task learning with a handcrafted feature, which does not provide robust sentence representation. Recently, hierarchical attention networks have performed outstandingly well. However, when training such models as single-task learning, these models do not exhibit superior performance and robust latent feature representation in the case of a small amount of data, specifically on the Arabic language, which is considered a low-resource language. Moreover, these models are based on single task learning and do not consider the related tasks, such as ternary and binary tasks (cross-task transfer). Centered on these shortcomings, we regard five ternary tasks as relative. We propose a multitask learning model based on hierarchical attention network (MTLHAN) to learn the best sentence representation and model generalization, with shared word encoder and attention network across both tasks, by training three-polarity and five-polarity Arabic sentiment analysis tasks alternately and jointly. Experimental results showed outstanding performance of the proposed model, with high accuracy of 83.98%, 87.68%, and 84.59 on LABR, HARD, and BRAD datasets, respectively, and a minimum macro mean absolute error of 0.632% on the Arabic tweets dataset for five-point Arabic sentiment classification problem. more...

MODIS land surface temperature data (MODIS Ts) products are quantified from the earth surface’s reflected thermal infrared signal via sensors onboard the Terra and Aqua satellites. MODIS Ts products are a great value to many environmental applications but often subject to discrepancies when compared to the air temperature (Ta) data that represent the temperature measured at 2 m above the ground surface. Although they are different in their nature, the relationship between Ts and Ta has been established by many researchers. Further validation and correction on the relationship between these two has enabled the estimation of Ta from MODIS Ts products in order to overcome the limitation of Ta that can only provide data in a point form with a very limited area coverage. Therefore, this study was conducted with the objective to assess the accuracy of MODIS Ts products, i.e., MOD11A1, MOD11A2, MYD11A1, and MYD11A2 against Ta and to identify the performance of a modified Linear Scaling using a constant and monthly correction factor (LS-MBC), and Quantile Mapping Mean Bias Correction (QM-MBC) methods for lowland area of Peninsular Malaysia. Furthermore, the correction factor (CF) values for each MBC were adjusted according to the condition set depending on the different bias levels. Then, the performance of the pre- and post-MBC correction for by stations and regions analysis were evaluated through root mean square error (RMSE), percentage bias (PBIAS), mean absolute error (MAE), and correlation coefficient (r). The region dataset is obtained by stacking the air temperature (Ta_r) and surface temperature (Ts_r) data corresponding to the number of stations within the identified regions. The assessment of pre-MBC data for both 36 stations and 5 regions demonstrated poor correspondence with high average errors and percentage biases, i.e., RMSE = 3.33–5.42 °C, PBIAS = 1.36–12.07%, MAE = 2.88–4.89 °C, and r = 0.16–0.29. The application of the MBCs has successfully reduced the er more...

Limited approaches have been applied to Arabic sentiment analysis for a five-point classification problem. These approaches are based on single task learning with a handcrafted feature, which does not provide robust sentence representation. Recently, hierarchical attention networks have performed outstandingly well. However, when training such models as single-task learning, these models do not exhibit superior performance and robust latent feature representation in the case of a small amount of data, specifically on the Arabic language, which is considered a low-resource language. Moreover, these models are based on single task learning and do not consider the related tasks, such as ternary and binary tasks (cross-task transfer). Centered on these shortcomings, we regard five ternary tasks as relative. We propose a multitask learning model based on hierarchical attention network (MTLHAN) to learn the best sentence representation and model generalization, with shared word encoder and attention network across both tasks, by training three-polarity and five-polarity Arabic sentiment analysis tasks alternately and jointly. Experimental results showed outstanding performance of the proposed model, with high accuracy of 83.98%, 87.68%, and 84.59 on LABR, HARD, and BRAD datasets, respectively, and a minimum macro mean absolute error of 0.632% on the Arabic tweets dataset for five-point Arabic sentiment classification problem. more...

MODIS land surface temperature data (MODIS Ts) products are quantified from the earth surface’s reflected thermal infrared signal via sensors onboard the Terra and Aqua satellites. MODIS Ts products are a great value to many environmental applications but often subject to discrepancies when compared to the air temperature (Ta) data that represent the temperature measured at 2 m above the ground surface. Although they are different in their nature, the relationship between Ts and Ta has been established by many researchers. Further validation and correction on the relationship between these two has enabled the estimation of Ta from MODIS Ts products in order to overcome the limitation of Ta that can only provide data in a point form with a very limited area coverage. Therefore, this study was conducted with the objective to assess the accuracy of MODIS Ts products, i.e., MOD11A1, MOD11A2, MYD11A1, and MYD11A2 against Ta and to identify the performance of a modified Linear Scaling using a constant and monthly correction factor (LS-MBC), and Quantile Mapping Mean Bias Correction (QM-MBC) methods for lowland area of Peninsular Malaysia. Furthermore, the correction factor (CF) values for each MBC were adjusted according to the condition set depending on the different bias levels. Then, the performance of the pre- and post-MBC correction for by stations and regions analysis were evaluated through root mean square error (RMSE), percentage bias (PBIAS), mean absolute error (MAE), and correlation coefficient (r). The region dataset is obtained by stacking the air temperature (Ta_r) and surface temperature (Ts_r) data corresponding to the number of stations within the identified regions. The assessment of pre-MBC data for both 36 stations and 5 regions demonstrated poor correspondence with high average errors and percentage biases, i.e., RMSE = 3.33–5.42 °C, PBIAS = 1.36–12.07%, MAE = 2.88–4.89 °C, and r = 0.16–0.29. The application of the MBCs has successfully reduced the er more...

Nowadays authentication considered the most vital field in term of security aspects because it represents the first line of defense in total process of our assets protection. In order to get access to any data especially when they are private, authentication is required as the first step of protecting accessing our assets. Therefore, many techniques been invented to create appropriate authentication process, for example the traditional textual password technique, the graphical passwords techniques and biometrics techniques. These techniques involved a sequence of procedures all aim to three things (confidentiality against attackers, acceleration of access time, simplification of the created technique). However, the rapid growth of threats for example the shoulder surfing attacks led to invent many techniques concentrated only on the confidentiality aspect and neglected other important aspects like easiness of utilization, as a result; these techniques suffered distinctly the issue of complexity. Many techniques been proposed in order to eliminate the complexity problem without losing their confidentiality purpose, however; most of them did not succeeded. For that reason, this research present a new hybrid technique that combines the maintenance of confidentiality against shoulder surfing attacks and the simplification of utilization at the same time, our technique consist of two simple techniques but effective to solve complexity issue with maintaining the confidentiality aspect, these two techniques are the traditional textual password and the graphical password. more...

Nowadays authentication considered the most vital field in term of security aspects because it represents the first line of defense in total process of our assets protection. In order to get access to any data especially when they are private, authentication is required as the first step of protecting accessing our assets. Therefore, many techniques been invented to create appropriate authentication process, for example the traditional textual password technique, the graphical passwords techniques and biometrics techniques. These techniques involved a sequence of procedures all aim to three things (confidentiality against attackers, acceleration of access time, simplification of the created technique). However, the rapid growth of threats for example the shoulder surfing attacks led to invent many techniques concentrated only on the confidentiality aspect and neglected other important aspects like easiness of utilization, as a result; these techniques suffered distinctly the issue of complexity. Many techniques been proposed in order to eliminate the complexity problem without losing their confidentiality purpose, however; most of them did not succeeded. For that reason, this research present a new hybrid technique that combines the maintenance of confidentiality against shoulder surfing attacks and the simplification of utilization at the same time, our technique consist of two simple techniques but effective to solve complexity issue with maintaining the confidentiality aspect, these two techniques are the traditional textual password and the graphical password. more...

Today, the advances in technology have led to the use of smart phones in health practices. In this paper, an android-based mobile application named GroRecipe, a meal planner system is developed. The main objective of developing GroRecipe is to encourage the practice of a healthy lifestyle. This can be achieved by making the meal planning effortless, healthy and tasty. GroRecipe can also speed up the meal preparation process by helping the user to estimate the amount of ingredients needed of a recipe based on the number of serving size per meal. It also provides the feature to auto generate the grocery lists, making the grocery purchasing decisions easier. Users can also enjoy using GroRecipe by sharing their recipe with others and rating the recipes posted by others. This can help to improve the quality of cooking in terms of its taste with healthy ingredients. The technologies used to develop the GroRecipe are Java, as the programming language, Firebase cloud, as the database and Android Studio as the IDE. more...

Today, the advances in technology have led to the use of smart phones in health practices. In this paper, an android-based mobile application named GroRecipe, a meal planner system is developed. The main objective of developing GroRecipe is to encourage the practice of a healthy lifestyle. This can be achieved by making the meal planning effortless, healthy and tasty. GroRecipe can also speed up the meal preparation process by helping the user to estimate the amount of ingredients needed of a recipe based on the number of serving size per meal. It also provides the feature to auto generate the grocery lists, making the grocery purchasing decisions easier. Users can also enjoy using GroRecipe by sharing their recipe with others and rating the recipes posted by others. This can help to improve the quality of cooking in terms of its taste with healthy ingredients. The technologies used to develop the GroRecipe are Java, as the programming language, Firebase cloud, as the database and Android Studio as the IDE. more...

Time series analysis is one of the major techniques in capturing trends and pattern of the occurrence for future forecasting. Existing but scarce work have developed temporal-based techniques which target to either predict movement (increase or decrease) or quantify the possibility of the predicted event to happen. Man of these techniques focus on the values of the time series attribute but there is no available work on dengue or intrusion logs that focus on temporal trend analysis based on temporal relations mining. In this work the proposed technique utilize the temporal trends analysis of the observational attributes towards the pattern of the target’s attribute values. In this work, we propose a new temporal trends analysis approach that uses temporal relation mining in forecasting dengue outbreak and cyber intrusion.We leverage the temporal abstractions and temporal logic to define patterns with the goal to optimize prediction accuracy. From the experiment conducted, the results showed that the proposed approach has better prediction as compared to the baseline. more...

The complexities and tangles of Arabic dialect in orthography and morphology typically make the sentimental analysis quite challenging. Moreover, most of the classification approaches have addressed this problem based on hand-crafted features. Since the Arabic language has multi-dialects and the language has no word-based order, the extraction process and the classification tasks are more difficult and time consuming. Deep neural network approaches applied to the Arabic language colloquial are very limited. These deep learning approaches typically comprise a structure that is very complex for small quantities of data. The structures are based on wide convolutional networks that are not capable of capturing the entire semantic and sentiment features for Arabic dialects. In this paper, a narrow structure of the convolutional neural network (CNN) has been proposed in order to obtain the tweets representations and classify the Arabic tweets into five, three and two polarities. Sensitivity analysis has been conducted to evaluate the impact of various combination structural properties, such as the number of convolutional filters, pooling size, and filter size on the classification performances. The proposed Arabic narrow convolutional neural network (NCNN) has captured the entire semantic and sentiment information contained in the tweet by maximizing the features of the detector's range. The NCNN performances were estimated to be at its optimum when structured by three convolutional layers, each one followed by the max pooling layer. The model has been developed without using lexicon resources and lexical features or augmented the dataset with extra training data. The narrow model is the first baseline model for Arabic dialects sentiment classifications for a sentence level as it is the first narrow CNN model addressing the Arabic Dialect tweets. NCNN model achieved the lowest macro average mean absolute error (MAE M ) for five polarity and higher Macro average recall (P) more...

The complexities and tangles of Arabic dialect in orthography and morphology typically make the sentimental analysis quite challenging. Moreover, most of the classification approaches have addressed this problem based on hand-crafted features. Since the Arabic language has multi-dialects and the language has no word-based order, the extraction process and the classification tasks are more difficult and time consuming. Deep neural network approaches applied to the Arabic language colloquial are very limited. These deep learning approaches typically comprise a structure that is very complex for small quantities of data. The structures are based on wide convolutional networks that are not capable of capturing the entire semantic and sentiment features for Arabic dialects. In this paper, a narrow structure of the convolutional neural network (CNN) has been proposed in order to obtain the tweets representations and classify the Arabic tweets into five, three and two polarities. Sensitivity analysis has been conducted to evaluate the impact of various combination structural properties, such as the number of convolutional filters, pooling size, and filter size on the classification performances. The proposed Arabic narrow convolutional neural network (NCNN) has captured the entire semantic and sentiment information contained in the tweet by maximizing the features of the detector's range. The NCNN performances were estimated to be at its optimum when structured by three convolutional layers, each one followed by the max pooling layer. The model has been developed without using lexicon resources and lexical features or augmented the dataset with extra training data. The narrow model is the first baseline model for Arabic dialects sentiment classifications for a sentence level as it is the first narrow CNN model addressing the Arabic Dialect tweets. NCNN model achieved the lowest macro average mean absolute error (MAE M ) for five polarity and higher Macro average recall (P) more...

Time series analysis is one of the major techniques in capturing trends and pattern of the occurrence for future forecasting. Existing but scarce work have developed temporal-based techniques which target to either predict movement (increase or decrease) or quantify the possibility of the predicted event to happen. Man of these techniques focus on the values of the time series attribute but there is no available work on dengue or intrusion logs that focus on temporal trend analysis based on temporal relations mining. In this work the proposed technique utilize the temporal trends analysis of the observational attributes towards the pattern of the target’s attribute values. In this work, we propose a new temporal trends analysis approach that uses temporal relation mining in forecasting dengue outbreak and cyber intrusion.We leverage the temporal abstractions and temporal logic to define patterns with the goal to optimize prediction accuracy. From the experiment conducted, the results showed that the proposed approach has better prediction as compared to the baseline. more...

Integration of heterogeneous data sources is a crucial step in big data analytics, although it creates ambiguity issues during mapping between the sources due to the variation in the query terms, data structure and granularity conflicts. However, there are limited researches on effective big data integration to address the ambiguity issue for big data analytics. This paper introduces a self-adaptive model for big data integration by exploiting the data structure during querying in order to mitigate and resolve ambiguities. An assessment of a preliminary work on the Geography and Quran dataset is reported to illustrate the feasibility of the proposed model that motivates future work such as solving complex query. more...

Dengue has become rapidly expanding and significant public health problem in tropical and subtropical regions. In severe cases, people infected with dengue may experience severe bleeding, shock and death. Thus, increasing dengue fever (DF) can be very serious, potentially life threatening and becoming global threat. Therefore, this research aimed to develop an accurate model that could better detect early signs and symptoms of dengue fever and develop a practical system for self-notification of the disease. Two techniques were applied to provide early self-notification to the patients namely the fuzzy expert system and data mining technique. The rules of dengue diagnosis are developed based on an interview with a medical doctor and those rules will be applied in an expert system using a fuzzy logic. However, before applying the extracted rules, the accuracy of rules was tested by data mining tool. This research applies the methodology to dengue related-data from a hospital and compares the rules to the training dataset by Multilayer Perceptron network. Furthermore, the finding showed that the accuracy of result for self-diagnosis of dengue symptoms produce a reliable result. more...

Dengue has become rapidly expanding and significant public health problem in tropical and subtropical regions. In severe cases, people infected with dengue may experience severe bleeding, shock and death. Thus, increasing dengue fever (DF) can be very serious, potentially life threatening and becoming global threat. Therefore, this research aimed to develop an accurate model that could better detect early signs and symptoms of dengue fever and develop a practical system for self-notification of the disease. Two techniques were applied to provide early self-notification to the patients namely the fuzzy expert system and data mining technique. The rules of dengue diagnosis are developed based on an interview with a medical doctor and those rules will be applied in an expert system using a fuzzy logic. However, before applying the extracted rules, the accuracy of rules was tested by data mining tool. This research applies the methodology to dengue related-data from a hospital and compares the rules to the training dataset by Multilayer Perceptron network. Furthermore, the finding showed that the accuracy of result for self-diagnosis of dengue symptoms produce a reliable result. more...

Observation satellites orbiting the Earth provide important surveillance information that helps in identifying various types of land cover. As such, the resolution of satellite images is critical to ensure high accuracy in classifying land cover types. Clearly, high-resolution images are desirable, but such images are prohibitively expensive. Hence, the use of medium-resolution satellite images seems more economical and practical. Several techniques have been developed to monitor the conditions of land covers across the world, such as aerial photography, ground survey, and remote sensing. Among the three techniques, remote sensing is the best, given its ability to monitor vast geographical areas more accurately and much faster compared to those of the other two techniques. In recent decades, many countries have been relying on remote sensing to monitor the conditions of coastal areas by extracting shorelines from satellite images. To date, several pixel-based methods have been proposed for the extraction of shorelines, but most of these methods are fraught with problems. Thus, the object-based approach is proposed using a combination of segmentation algorithms, namely Felzenswalb, Quickshift, and SLIC, together with 15 machine learning classifiers, to classify segmented images of Langkawi Island. The performance of the segmentation algorithms and machine learning classifiers were assessed in terms of segmentation time and overall accuracy in four experimental settings comprising of three different parameters. The research findings showed that the proposed hybridization of SLIC segmentation and Extra Tree classifier was the most efficient and accurate technique compared to other combinations of techniques in extracting the shoreline of the study area. Specifically, SLIC was faster than Felzenswalb and Quickshift by as much as 37 times and 500 times, respectively. Together with Extra Tree classifier, SLIC managed to achieve 100% overall accuracy in the object-based cl more...

Monitoring and measuring the shoreline of coastal zones helps establish the boundary of a country. Such an activity entails ground survey, topographic survey, aerial photo, or remote sensing techniques to extract the shoreline. For example, the remote sensing technique to determine shorelines involves the extraction of relevant data from satellite images. Specifically, the satellite image classification enables shorelines to be extracted from land and water classes with a high degree of precision. However, extracting information from satellite images is challenging as it relies on a strong understanding of image processing, machine learning, and data mining techniques. Thus, the researchers discuss the study of the pixel-based classification of machine learning techniques to classify land and water classes in terms of accuracy, training time, and testing time. The research findings showed that the Multilayer Perceptron Artificial Neural Network (MLP ANN) was the most effective technique, compared with other techniques, hence reinforcing its importance in classifying land and water classes. more...

Monitoring and measuring the shoreline of coastal zones helps establish the boundary of a country. Such an activity entails ground survey, topographic survey, aerial photo, or remote sensing techniques to extract the shoreline. For example, the remote sensing technique to determine shorelines involves the extraction of relevant data from satellite images. Specifically, the satellite image classification enables shorelines to be extracted from land and water classes with a high degree of precision. However, extracting information from satellite images is challenging as it relies on a strong understanding of image processing, machine learning, and data mining techniques. Thus, the researchers discuss the study of the pixel-based classification of machine learning techniques to classify land and water classes in terms of accuracy, training time, and testing time. The research findings showed that the Multilayer Perceptron Artificial Neural Network (MLP ANN) was the most effective technique, compared with other techniques, hence reinforcing its importance in classifying land and water classes. more...

Observation satellites orbiting the Earth provide important surveillance information that helps in identifying various types of land cover. As such, the resolution of satellite images is critical to ensure high accuracy in classifying land cover types. Clearly, high-resolution images are desirable, but such images are prohibitively expensive. Hence, the use of medium-resolution satellite images seems more economical and practical. Several techniques have been developed to monitor the conditions of land covers across the world, such as aerial photography, ground survey, and remote sensing. Among the three techniques, remote sensing is the best, given its ability to monitor vast geographical areas more accurately and much faster compared to those of the other two techniques. In recent decades, many countries have been relying on remote sensing to monitor the conditions of coastal areas by extracting shorelines from satellite images. To date, several pixel-based methods have been proposed for the extraction of shorelines, but most of these methods are fraught with problems. Thus, the object-based approach is proposed using a combination of segmentation algorithms, namely Felzenswalb, Quickshift, and SLIC, together with 15 machine learning classifiers, to classify segmented images of Langkawi Island. The performance of the segmentation algorithms and machine learning classifiers were assessed in terms of segmentation time and overall accuracy in four experimental settings comprising of three different parameters. The research findings showed that the proposed hybridization of SLIC segmentation and Extra Tree classifier was the most efficient and accurate technique compared to other combinations of techniques in extracting the shoreline of the study area. Specifically, SLIC was faster than Felzenswalb and Quickshift by as much as 37 times and 500 times, respectively. Together with Extra Tree classifier, SLIC managed to achieve 100% overall accuracy in the object-based cl more...

Integration of heterogeneous data sources is a crucial step in big data analytics, although it creates ambiguity issues during mapping between the sources due to the variation in the query terms, data structure and granularity conflicts. However, there are limited researches on effective big data integration to address the ambiguity issue for big data analytics. This paper introduces a self-adaptive model for big data integration by exploiting the data structure during querying in order to mitigate and resolve ambiguities. An assessment of a preliminary work on the Geography and Quran dataset is reported to illustrate the feasibility of the proposed model that motivates future work such as solving complex query. more...

Temperature has major influence in insect development and outbreak. At present, the common method of collecting temperature information mainly relies on ground weather stations. However, this method is unfeasible for a large-scale area as weather stations distributions are sparse. This, however, can be compensated by the temperature measured through remote sensing satellites known as Land Surface Temperature (LST). Hence, this paper reviews the advantages and disadvantages of Thermal Infrared (TIR) and Microwave (MW) sensors for the acquisition of LST. This review will focus on the availability, suitability and adaptability of those sensors in providing LST for insect pest monitoring with the comparison being concentrated on their spatial and temporal characteristics, along with their accuracies. more...

Shoreline extraction provides the boundary information of land and water, which helps monitor erosions or accretions of coastal zones. Such monitoring can be performed by using satellite images rather than by using traditional ground survey. To date, shorelines can be extracted from satellite images with a high degree of accuracy by using satellite image classification techniques based on machine learning, which helps identify the land and water classes of shorelines. In this study, the results of extracted shorelines of 11 classifiers were validated by using a reference shoreline provided by the local authority. Specifically, the validation assessment was performed using Mean Shoreline Change method to examine the differences between the extracted shorelines and the reference shoreline. The research findings showed that SVM Linear attained the highest number of transects and the lowest mean distances between extracted shorelines and reference shoreline, thus rendering it as the most effective image classification technique in demarcating land and water classes. Furthermore, the findings showed that the accuracy of the extracted shoreline was not directly proportional to the accuracy of the image classification, and smoothing operation using PAEK affected the quality of extracted shorelines. Moreover, the tolerance setting that was ten times the spatial resolution of satellite images was observed to be the most optimal configuration. more...

Coastal zones are constantly exposed to changes caused by natural processes, anthropogenic activities or both, which can precariously alter the coastal landscapes of many countries. Thus, monitoring of coastal zones is needed to provide important information about current conditions of a countrys coastal areas by examining changes that are taking place. In this respect, such monitoring can be carried out by traditional ground survey, airborne aerial photo, or remote sensing. However, the former is more effective and efficient as it can extract vital boundary information from satellite images using appropriate image analysis. Nonetheless, shoreline extraction has a number of challenges, and many methods have been proposed to improve such extraction, such as the use of machine learning methods. Thus, this study was carried out to determine the most effective ensemble voting classifier based on two different types of classifiers, comprising 11 single classifiers and 4 ensemble classifiers. Performance criteria of the classifiers were based on the overall accuracy, training time, and testing time. The analysis of the experimental data revealed several interesting results. First, for the combination of single and ensemble classifiers, ensemble classifiers with majority voting of Random Forest and Support Vector Machine RBF kernel were the most effective classifiers, attaining high overall accuracy. Second, for the combination of two single classifiers, Multilayer Perceptron and k-Nearest Neighbor attained high overall accuracy, rendering them as the most effective classifiers in this category of classifiers. Third, there were trade-offs between performance measures, as increased overall accuracy was accompanied by longer training and testing time in the performance of such classifiers as both of voting-based ensemble classifiers increased significantly. more...

Coastal zones are constantly exposed to changes caused by natural processes, anthropogenic activities or both, which can precariously alter the coastal landscapes of many countries. Thus, monitoring of coastal zones is needed to provide important information about current conditions of a countrys coastal areas by examining changes that are taking place. In this respect, such monitoring can be carried out by traditional ground survey, airborne aerial photo, or remote sensing. However, the former is more effective and efficient as it can extract vital boundary information from satellite images using appropriate image analysis. Nonetheless, shoreline extraction has a number of challenges, and many methods have been proposed to improve such extraction, such as the use of machine learning methods. Thus, this study was carried out to determine the most effective ensemble voting classifier based on two different types of classifiers, comprising 11 single classifiers and 4 ensemble classifiers. Performance criteria of the classifiers were based on the overall accuracy, training time, and testing time. The analysis of the experimental data revealed several interesting results. First, for the combination of single and ensemble classifiers, ensemble classifiers with majority voting of Random Forest and Support Vector Machine RBF kernel were the most effective classifiers, attaining high overall accuracy. Second, for the combination of two single classifiers, Multilayer Perceptron and k-Nearest Neighbor attained high overall accuracy, rendering them as the most effective classifiers in this category of classifiers. Third, there were trade-offs between performance measures, as increased overall accuracy was accompanied by longer training and testing time in the performance of such classifiers as both of voting-based ensemble classifiers increased significantly. more...

Shoreline extraction provides the boundary information of land and water, which helps monitor erosions or accretions of coastal zones. Such monitoring can be performed by using satellite images rather than by using traditional ground survey. To date, shorelines can be extracted from satellite images with a high degree of accuracy by using satellite image classification techniques based on machine learning, which helps identify the land and water classes of shorelines. In this study, the results of extracted shorelines of 11 classifiers were validated by using a reference shoreline provided by the local authority. Specifically, the validation assessment was performed using Mean Shoreline Change method to examine the differences between the extracted shorelines and the reference shoreline. The research findings showed that SVM Linear attained the highest number of transects and the lowest mean distances between extracted shorelines and reference shoreline, thus rendering it as the most effective image classification technique in demarcating land and water classes. Furthermore, the findings showed that the accuracy of the extracted shoreline was not directly proportional to the accuracy of the image classification, and smoothing operation using PAEK affected the quality of extracted shorelines. Moreover, the tolerance setting that was ten times the spatial resolution of satellite images was observed to be the most optimal configuration. more...

Temperature has major influence in insect development and outbreak. At present, the common method of collecting temperature information mainly relies on ground weather stations. However, this method is unfeasible for a large-scale area as weather stations distributions are sparse. This, however, can be compensated by the temperature measured through remote sensing satellites known as Land Surface Temperature (LST). Hence, this paper reviews the advantages and disadvantages of Thermal Infrared (TIR) and Microwave (MW) sensors for the acquisition of LST. This review will focus on the availability, suitability and adaptability of those sensors in providing LST for insect pest monitoring with the comparison being concentrated on their spatial and temporal characteristics, along with their accuracies. more...

Cloud computing becomes a powerful trend in the development of ICT services. It allows dynamic resource scaling from infinite resource pool for supporting Cloud users. Such scenario leads to necessity of larger size of computing infrastructure and increases processing power. Demand on the cloud computing is continually growth that makes it changes to scope of green cloud computing. It aims to reduce energy consumption in Cloud computing while maintaining a better performance. However, there is lack of performance metric that analyzing trade-off between energy consumption and performance. Considering high volume of mixed users’ requirements and diversity of services offered; an appropriate performance model for achieving better balance between Cloud performance and energy consumption is needed. In this work, we focus on green Cloud Computing through scheduling optimization model. Specifically, we investigate a relationship between performance metrics that chosen in scheduling approaches with energy consumption for energy efficiency. Through such relationship, we develop an energy-based performance model that provides a clear picture on parameter selection in scheduling for effective energy management. We believed that better understanding on how to model the scheduling performance will lead to green Cloud computing. more...

Early prediction of diseases especially dengue fever in the case of Malaysia, is very crucial to enable health authorities to develop response strategies and context preventive intervention programs such as awareness campaigns for the high risk population before an outbreak occurs. Some of the deficiencies in dengue epidemiology are insufficient awareness on the parameter as well as the combination among them. Most of the studies on dengue prediction use standalone models which face problem of finding the appropriate parameter since they need to apply try and error approach. The aim of this paper is to conduct experiments for determining the best network structure that has effective variable and fitting parameters in predicting the spread of the dengue outbreak. Four model structures were designed in order to attain optimum prediction performance. The best model structure was selected as predicting model to solve the time series prediction of dengue. The result showed that neighboring location of dengue cases was very effective in predicting the dengue outbreak and it is proven that the hybrid Genetic Algorithm and Neural Network (GANN) model significantly outperforms standalone models namely regression and Neural Network (NN). more...

Cloud computing becomes a powerful trend in the development of ICT services. It allows dynamic resource scaling from infinite resource pool for supporting Cloud users. Such scenario leads to necessity of larger size of computing infrastructure and increases processing power. Demand on the cloud computing is continually growth that makes it changes to scope of green cloud computing. It aims to reduce energy consumption in Cloud computing while maintaining a better performance. However, there is lack of performance metric that analyzing trade-off between energy consumption and performance. Considering high volume of mixed users’ requirements and diversity of services offered; an appropriate performance model for achieving better balance between Cloud performance and energy consumption is needed. In this work, we focus on green Cloud Computing through scheduling optimization model. Specifically, we investigate a relationship between performance metrics that chosen in scheduling approaches with energy consumption for energy efficiency. Through such relationship, we develop an energy-based performance model that provides a clear picture on parameter selection in scheduling for effective energy management. We believed that better understanding on how to model the scheduling performance will lead to green Cloud computing. more...

Early prediction of diseases especially dengue fever in the case of Malaysia, is very crucial to enable health authorities to develop response strategies and context preventive intervention programs such as awareness campaigns for the high risk population before an outbreak occurs. Some of the deficiencies in dengue epidemiology are insufficient awareness on the parameter as well as the combination among them. Most of the studies on dengue prediction use standalone models which face problem of finding the appropriate parameter since they need to apply try and error approach. The aim of this paper is to conduct experiments for determining the best network structure that has effective variable and fitting parameters in predicting the spread of the dengue outbreak. Four model structures were designed in order to attain optimum prediction performance. The best model structure was selected as predicting model to solve the time series prediction of dengue. The result showed that neighboring location of dengue cases was very effective in predicting the dengue outbreak and it is proven that the hybrid Genetic Algorithm and Neural Network (GANN) model significantly outperforms standalone models namely regression and Neural Network (NN). more...

Year 2010 massive flood hit the northern region of Peninsular Malaysia particularly Perlis and Kedah involved several districts and destroyed many agricultural areas and the infrastructure. This study focuses on the comparison between pixel-based classification and object-based classification of five machine learning algorithms including Parallelepiped (PP), Minimum Distance (MD), Maximum Likelihood (ML), Mahalanobis Distance (MH) and Neural Network (NN) using radar satellite image in extracting that flood extent. TerraSAR-X image was used to map the flood extent of the study area. In object-based approach, there were three simple machine learning algorithms such as PP, MD, MH together with NN performed with high accuracy while in pixel based approach, NN was the highest accuracy of all machine learning algorithms. The best output was chosen to be converted to vector format for mapping the flood extent. The result showed clearly through the map output that Kubang Pasu, Kota Setar and Kangar districts were highly affected by the flood. From the flood extent information, the collaboration of government, private sector, Non-governmental Organization (NGO) and community are needed to play the appropriate role in managing flood damage especially at the highly affected area and thus prevent loss of human live. Besides that, the authority could take action plan for pre-disaster, during and post-disaster caused by flooding. more...

Cloud computing becomes a powerful trend in the development of ICT services. Cloud providers typically try to provide high performance to their users while minimizing energy consumption in their operation. However, there is lack of performance metric that analyzing trade-off between performance and energy consumption. Considering high volume of mixed users’ requirements and diversity of services offered; an appropriate performance model for achieving better balance between Cloud performance and energy consumption is needed. One of resource management strategies for better performance is through effective scheduling approach. In this paper we investigate a relationship between performance metrics that chosen in existing scheduling approaches with energy consumption for energy efficiency. Through such relationship, we develop an energy-based performance modeling framework that provides a clear picture on parameter selection strategy for effective energy management. Our framework provides adaptive guideline for designing performance model explicitly for energy efficient scheduling. We believed that better understanding on how to model the scheduling performance will lead to green Cloud computing. more...

Cloud computing becomes a powerful trend in the development of ICT services. Cloud providers typically try to provide high performance to their users while minimizing energy consumption in their operation. However, there is lack of performance metric that analyzing trade-off between performance and energy consumption. Considering high volume of mixed users’ requirements and diversity of services offered; an appropriate performance model for achieving better balance between Cloud performance and energy consumption is needed. One of resource management strategies for better performance is through effective scheduling approach. In this paper we investigate a relationship between performance metrics that chosen in existing scheduling approaches with energy consumption for energy efficiency. Through such relationship, we develop an energy-based performance modeling framework that provides a clear picture on parameter selection strategy for effective energy management. Our framework provides adaptive guideline for designing performance model explicitly for energy efficient scheduling. We believed that better understanding on how to model the scheduling performance will lead to green Cloud computing. more...

Year 2010 massive flood hit the northern region of Peninsular Malaysia particularly Perlis and Kedah involved several districts and destroyed many agricultural areas and the infrastructure.This study focuses on the comparison between pixel-based classification and object-based classification of five machine learning algorithms including Parallelepiped (PP), Minimum Distance (MD), Maximum Likelihood (ML), Mahalanobis Distance (MH) and Neural Network (NN) using radar satellite image in extracting that flood extent. TerraSAR-X image was used to map the flood extent of the study area. In object-based approach, there were three simple machine learning algorithms such as PP, MD, MH together with NN performed with high accuracy while in pixel based approach, NN was the highest accuracy of all machine learning algorithms. The best output was chosen to be converted to vector format for mapping the flood extent.The result showed clearly through the map output that Kubang Pasu, Kota Setar and Kangar districts were highly affected by the flood. From the flood extent information, the collaboration of government, private sector, Non Governmental Organization (NGO) and community are needed to play the appropriate role in managing flood damage especially at the highly affected area and thus prevent loss of human live.Besides that, the authority could take action plan for pre-disaster, during and post-disaster caused by flooding. more...