Papers by Laila Abdelhamid
International journal of computer applications, Jan 22, 2024
Due to the numerous issues or challenges that aren't always within the company's control. Custome... more Due to the numerous issues or challenges that aren't always within the company's control. Customers became unhappy. Customer complaint is the method by which they convey their dissatisfaction. Due to the rapid advancement of technology and the various convenient channels available for customers to voice their complaints, including email, web, and chatbots, online complaints have experienced exponential growth. As a result, classifying these complaints under the pertinent issue in time became a difficult task. Selecting the appropriate classification model and Fitting it with the proper training and testing ratios is a crucial topic that always faces researchers. This paper implements and compares the performance of six text classification machine learning algorithms used in multiclassification (SVM, KNN, NB, DT, RF, and GB) under two types of sampling (random and stratified) with the use of
Research Square (Research Square), Mar 20, 2024
Infectious disease control is one of the most thrilling opportunities form using big data, where ... more Infectious disease control is one of the most thrilling opportunities form using big data, where these streams of novel data can be used to improve timeliness for preventing. Various public and private sector Healthcare providers generate, store, and analyse big data to improve the services they provide. Lately, the COVID-19-new Corona virus outbreak has put human health, life, production, social connections, and international relations in grave danger. Consequently, big data technologies have been crucial in the pandemic response. Infectious disease occurs when a person has a disease by a pathogen from another person. It is a problem that causes harm for both individual and macro scales. In addition, infectious illness patterns are unknown, which complicate the prediction process. This study aims to create big data framework to predict infectious diseases by discovering new symptoms patterns to enhance healthcare infection prevention and control. To achieve this goal, machine learning algorithms K-Nearest Neighbors (K-NN) and Random Forest (RF) were used to clean and maintain big data from December 2019 to June 2020. Additionally, the mining model FP-growth and Park, Chen, and Yu (PCY) of China were applied to discover new symptom rules. The results show that the RF model performs better than K-NN with accuracy rates of 97%, and the PCY model performs better than FP-growth with an accuracy rate of 98%. These results highlight the potential of big data and machine learning in identifying patterns and predicting infectious diseases, which can ultimately improve public health outcomes.
Big data and cognitive computing, Feb 6, 2024
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Data, Jan 25, 2024
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
The Role of Effective Complaint Handling For Business Sustainability: A Review Paper
International Journal of Global Business and Competitiveness, Dec 29, 2023
A Framework for Assessing Physical Rehabilitation Exercises
Multimedia tools and applications, Apr 12, 2024
Physical rehabilitation is crucial in healthcare, facilitating recovery from injuries or illnesse... more Physical rehabilitation is crucial in healthcare, facilitating recovery from injuries or illnesses and improving overall health. However, a notable global challenge stems from the shortage of professional physiotherapists, particularly acute in some developing countries, where the ratio can be as low as one physiotherapist per 100,000 individuals. To address these challenges and elevate patient care, the field of physical rehabilitation is progressively integrating Computer Vision and Human Activity Recognition (HAR) techniques. Numerous research efforts aim to explore methodologies that assist in rehabilitation exercises and evaluate patient movements, which is crucial as incorrect exercises can potentially worsen conditions. This study investigates applying various deep-learning models for classifying exercises using the benchmark KIMORE and UI-PRMD datasets. Employing Bi-LSTM, LSTM, CNN, and CNN-LSTM, alongside a Random Search for architectural design and Hyper-parameter tuning, our investigation reveals the (CNN) model as the top performer. After applying cross-validation, the technique achieves remarkable mean testing accuracy rates of 93.08% on the KIMORE dataset and 99.7% on the UI-PRMD dataset. This marks a slight improvement of 0.75% and 0.1%, respectively, compared to previous techniques. In addition, expanding beyond exercise classification, this study explores the KIMORE dataset's utility for disease identification, where the (CNN) model consistently demonstrates an outstanding accuracy of 89.87%, indicating its promising role in both exercises and disease identification within the context of physical rehabilitation.
E-Commerce Challenges, Definitions, Solutions and Evaluation
Journal of Computer Science
Retracted: Arabic feature-based level sentiment analysis using lexicon-based approach
Journal of Fundamental and Applied Sciences, May 23, 2018
The increase of opinionated users’ reviews on the web has raised the importance of analyzing and ... more The increase of opinionated users’ reviews on the web has raised the importance of analyzing and extracting useful information pieces from those reviews. Manually analyzing Thus, automatic consuming.theseopinions is costlyandtime mining techniques are highly desirable. By investigating the current state of automatic sentiment analysis tools, a lack of tools for analyzing languages rather than English was highly observed. This study proposes a feature-based sentiment analysis technique for mining Arabic user generated reviews. The extraction and weighting of sentiments and features are executed automatically from a set of unannotated reviews using Part Of Speech (POS) tagging feature and a set of linguistics rules. Similarity measurements have been used to assign primary weights to the sentiments. The collected features are organized into a tree structure representing the relationship between the objects being reviewed and their components. For extracting and analyzing feature-sentiment pairs five rules is applied. Finally, a lexicon-based classification is performed to evaluate the performance of each rule.The experimental results show that the proposed approach is able to automatically extract and sentiment ـidentifythe polarityfor alarge number of feature expressions and achieve high accuracy.
On Understanding Sports–HAR: Hierarchical, Mobile, Multi-Sensor based Classification of Table–Tennis Strokes
2023 Intelligent Methods, Systems, and Applications (IMSA)
Comparative Study Between Machine learning algorithms and feature ranking techniques on UI-PRMD dataset
Rehabilitation exercises reduce the demand for healthcare services over time by decreasing the nu... more Rehabilitation exercises reduce the demand for healthcare services over time by decreasing the number of hospital visits, lengths of stay, and readmissions. Since rehabilitation is a continuous process, it is crucial to monitor patient progress. This paper compares various machine learning classifiers which enable patients to perform exercises at home instead of visiting a physiotherapy center. The system assesses the correct performance of the exercises and tracks the patient's improvement, leading to lower rehabilitation costs. A distinct skeletal part, angle, and trajectory are required for each activity to distinguish between the workouts and assess whether they were executed correctly. Data extraction was performed using one Kinect camera, and six feature ranking algorithms were employed to construct the system, with the top features selected. Subsequently, 13 classical machine learning algorithms were implemented to identify the algorithm that produced the most accurate cl...
Feature-based sentiment analysis in online Arabic reviews
2016 11th International Conference on Computer Engineering & Systems (ICCES), 2016
Social media has given web users a venue for expressing and sharing their thoughts and opinions o... more Social media has given web users a venue for expressing and sharing their thoughts and opinions on different topics and events. Each day millions of user generated comments are raised on the web and analyzing these opinions to discover useful information pieces manually is costly and time-consuming. Thus, automatic mining techniques are highly desirable. By investigating the current state of automatic sentiment analysis tools, a lack of tools for analyzing languages rather than English was highly observed. Most of the researches on Opinion Mining are tailored for English language, and research on mining Arabic reviews is going in very slow rate. This study proposes a feature-based sentiment analysis technique for mining Arabic user generated reviews. The extraction and weighting of sentiments and features are executed automatically from a set of annotated reviews using Part Of Speech (POS) tagging feature. The collected features are organized into a tree structure representing the relationship between the objects being reviewed and their components. Furthermore, an automatic expandable approach of Arabic feature and sentiment words using free online Arabic lexicons and thesauruses is introduced. For extracting and analyzing feature-sentiment pairs five rules is proposed. Finally, a lexicon-based classification is performed to evaluate the performance of each rule. The experimental results show that the proposed approach is able to automatically extract and identify the polarity for a large number of feature-sentiment expressions and achieve high accuracy.
International Journal of Computer Applications
Carpooling or ride-sharing systems are considered to be an economical efficient method to solve m... more Carpooling or ride-sharing systems are considered to be an economical efficient method to solve many traffic problems. Carpooling allows drivers to share their journeys with other passengers. This reduces passenger fares and travel time, in addition to traffic congestion, while also increasing driver income. So, several carpooling systems have been introduced in recent years. This research proposed a ridesharing analysis framework to find the shortest route between any two carpooling system nodes. Also, to represent how the matching process between passengers and drivers can be performed in an economical and efficient method to study the profitability for passenger/s and driver/s. The framework was applied to real carsharing test data and the recorded results showed a 40% saving for passengers and a high level of added revenue for drivers compared to the existing systems in the market.
Increased on-peak loads requests have gotten quite possibly the most difficult issues addressed b... more Increased on-peak loads requests have gotten quite possibly the most difficult issues addressed by numerous<br> electric utilities and governments. Electricity power outages in developing nations are an everyday reality<br> because of expanded economic activities. Consequently, traditional electric grids are being changed into<br> smart grids (SGs) to address such issue of on-peak loads events. SGs enable "bi-directional" electricity and<br> data flow between electric utilities and end-uses, and utilize different gadgets deployed at power plants,<br> distribution centers and in customers' buildings for checking and control the grid functions. Consequently, a<br> SG requires automation, tracking and connectivity of such gadgets. This is accomplished via the applications<br> of Internet of Things (IoT). IoT supports different functions of SG frameworks through the generation,<br> transmission and utilization of energy by de...
IEEE Access, 2022
Frequent itemset mining (FIM) is a crucial tool for identifying hidden patterns in information. F... more Frequent itemset mining (FIM) is a crucial tool for identifying hidden patterns in information. FP-Growth is an FIM algorithm used to find associations. When the data size increases, the execution of FIM algorithms on a single machine suffers from computational problems, such as memory and time consumption. For these reasons, parallel and distributed processing on platforms such as Spark is essential. The parallel frequent pattern (PFP) is the implementation of FP-Growth in Spark. The main problem with PFP is that it does not consider the load balancing between cluster units. This research proposes an enhanced balanced parallel frequent pattern "EBPFP" algorithm to enhance and balance the PFP. The proposed algorithm (EBPFP) proposes two ideas. First, a strategy for load balancing between groups is proposed to ensure that the items are evenly divided between the nodes, and the cluster resources are used more effectively. Second, the improved conditional pattern base (ICPB) method aims to remove infrequent items from the conditional pattern base before constructing local FP-Trees. The experimental results show that the proposed EBPFP algorithm outperforms PFP, and the difference in running time between EBPFP and PFP was 21.56% and 39.72%, respectively.
Applications of IoT in Smart Grids Using Demand Respond for Minimizing On-peak Load, 2021
Increased on-peak loads requests have gotten quite possibly the most difficult issues addressed b... more Increased on-peak loads requests have gotten quite possibly the most difficult issues addressed by numerous electric utilities and governments. Electricity power outages in developing nations are an everyday reality because of expanded economic activities. Consequently, traditional electric grids are being changed into smart grids (SGs) to address such issue of on-peak loads events. SGs enable "bi-directional" electricity and data flow between electric utilities and end-uses, and utilize different gadgets deployed at power plants, distribution centers and in customers' buildings for checking and control the grid functions. Consequently, a SG requires automation, tracking and connectivity of such gadgets. This is accomplished via the applications of Internet of Things (IoT). IoT supports different functions of SG frameworks through the generation, transmission and utilization of energy by deploying IoT gadgets (like sensors), just as by giving the
Towards Enhancing the Performance of Parallel FP-Growth on Spark
IEEE Access, 2022
Frequent itemset mining (FIM) is a crucial tool for identifying hidden patterns in information. F... more Frequent itemset mining (FIM) is a crucial tool for identifying hidden patterns in information. FP-Growth is an FIM algorithm used to find associations. When the data size increases, the execution of FIM algorithms on a single machine suffers from computational problems, such as memory and time consumption. For these reasons, parallel and distributed processing on platforms such as Spark is essential. The parallel frequent pattern (PFP) is the implementation of FP-Growth in Spark. The main problem with PFP is that it does not consider the load balancing between cluster units. This research proposes an enhanced balanced parallel frequent pattern “EBPFP” algorithm to enhance and balance the PFP. The proposed algorithm (EBPFP) proposes two ideas. First, a strategy for load balancing between groups is proposed to ensure that the items are evenly divided between the nodes, and the cluster resources are used more effectively. Second, the improved conditional pattern base (ICPB) method aim...
Future Computing and Informatics Journal, 2020
Colon cancer is also referred to as colorectal cancer, a kind of cancer that starts with colon da... more Colon cancer is also referred to as colorectal cancer, a kind of cancer that starts with colon damage to the large intestine in the last section of the digestive tract. Elderly people typically suffer from colon cancer, but this may occur at any age.It normally starts as little, noncancerous (benign) mass of cells named polyps that structure within the colon. After a period of time these polyps can turn into advanced malignant tumors that attack the human body and some of these polyps can become colon cancers. So far, no concrete causes have been identified and the complete cancer treatment is very difficult to be detected by doctors in the medical field. Colon cancer often has no symptoms in early stage so detecting it at this stage is curable but colorectal cancer diagnosis in the final stages (stage IV), gives it the opportunity to spread to different pieces of the body, difficult to treat successfully, and the person's chances of survival are much lower. False diagnosis of c...
This research proposed ontologies to retain information and knowledge for overcoming pesticide pa... more This research proposed ontologies to retain information and knowledge for overcoming pesticide paradox in model based testing. Domain ontology was constructed, which described the vocabularies related to a software engineering domain. The ontology retained the structure of a Polymorphism State Collaboration Class Test Model (PSCCTEM) by defining the test model's structural elements and the relationships between them. In this research, the rules for transforming UML PSCCTEM test model into behavioral model ontology, proposed based on the Ontology Definition Metamodel (ODM). The proposed solution argued that developing a new testing phase that help the user to regenerate the test steps easily according to system modifications that will overcome pesticide paradox.<br> Keywords: Ontologies; pesticide paradox; software engineering; Ontology Definition Metamodel (ODM).
Uploads
Papers by Laila Abdelhamid