Search

Most companies use social media data for business. Sentiment analysis automatically gathers analyses and summarizes this type of data. Managing unstructured social media data is difficult. Noisy data is a challenge to sentiment analysis. Since over 50% of the sentiment analysis process is data pre-processing, processing big social media data is challenging too. If pre-processing is carried out correctly, data accuracy may improve. Also, sentiment analysis workflow is highly dependent. Because no pre-processing technique works well in all situations or with all data sources, choosing the most important ones is crucial. Prioritization is an excellent technique for choosing the most important ones. As one of many Multi-Criteria Decision Making (MCDM) methods, the Analytic Hierarchy Process (AHP) is preferred for handling complicated decision-making challenges using several criteria. The Consistency Ratio (CR) scores were used to examine pair-wise comparisons to evaluate the AHP. This study used two judgment scales to get the most consistent judgment. Firstly, the Saaty judgment scale (SS), then the Generalized Balanced Scale (GBS). It investigated whether two different AHP judgment scales would affect decision-making. The main criteria for prioritizing pre-processing techniques in sentiment analysis are Punctuation, Spelling, Number, and Context. These four criteria also contain sub-criteria. GBS pair-wise comparisons are closer to the CR value than SS, reducing the alternatives’ weight ratios. This paper explains how AHP aids logical decision-making. Prioritizing pre-processing techniques with AHP can be a paradigm for other sentiment analysis stages. In short, this paper adds another contribution to the Big Data Analytics domain.

Nowadays, people's expression on the Internet is no longer limited to text, especially with the rise of the short video boom, leading to the emergence of a large number of modal data such as text, pictures, audio, and video. Compared to single mode data ,the multi-modal data always contains massive information. The mining process of multi-modal information can help computers to better understand human emotional characteristics. However, because the multi-modal data show obvious dynamic time series features, it is necessary to solve the dynamic correlation problem within a single mode and between different modes in the same application scene during the fusion process. To solve this problem, in this paper, a feature extraction framework of the three-dimensional dynamic expansion is established based on the common multi-modal data, for example video , sound ,text.Based on the framework, a multi-modal fusion-matched framework based on spatial and temporal feature enhancement, respectively to solve the dynamic correlation within and between modes, and then model the short and long term dynamic correlation information between different modes based on the proposed framework. Multiple group experiments performed on MOSI datasets show that the emotion recognition model constructed based on the framework proposed here in this paper can better utilize the more complex complementary information between different modal data. Compared with other multi-modal data fusion models, the spatial-temporal attention-based multimodal data fusion framework proposed in this paper significantly improves the emotion recognition rate and accuracy when applied to multi-modal emotion analysis, so it is more feasible and effective.

Blockchain is an innovative technology that has gained interest in all sectors in the era of digital transformation where it manages transactions and saves them in a database. With the increasing financial transactions and the rapidly developed society with growing businesses many people looking for the dream of a better financially independent life, stray from large corporations and organizations to form startups and small businesses. Recently, the increasing demand for employees or institutes to prepare and manage contracts, papers, and the verifications process, in addition to human mistakes led to the emergence of a smart contract. The smart contract has been developed to save time and provide more confidence while dealing, as well as to cover the security aspects of digital management and to solve negotiation concerns. The smart contract was employed in creating a distributed ledger to eliminate the need for centralization. In this paper, a simple prototype has been implemented for the smart contract integrated with blockchain which is simulated in a local server with a set of nodes. Several security objectives, such as confidentiality, authorization, integrity, and non-repudiation, have been achieved in the proposed system. Besides, the paper discussed the importance of using the Blockchain technique, and how it contributed to the management of transactions in addition to how it was implemented in highly transparent real-estate scenarios. The smart contract was employed in creating a distributed ledger to eliminate the need for centralization. The elliptic-curve public key has been adopted as an alternative for the RSA in a signature generation/verification process and encryption protocol. For secure transactions, The Secure Socket Layer (SSL) also has been adopted as a secure layer in the web browser. The results have been investigated and evaluated from different aspects and the implementation was in a restricted environment. Experiments showed us the complexity of time and cost when using the (ECC) algorithm and using (RSA) algorithm depending on the size and length of the key. So if the size of the key in (ECC) equals (160) bits, and it corresponds to (1024) bits in (RSA), which is equivalent to 40% for (ECC) and 30% for (RSA). As a result, the (ECC) algorithm is complex, its key is smaller and the process of generating the key is faster, so it has achieved a high level of security.

The use of silicon carbide is increasing significantly in the fields of research and technology. Topological indices enable data gathering on algebraic graphs and provide a mathematical framework for analyzing the chemical structural characteristics. In this paper, well-known degree-based topological indices are used to analyze the chemical structures of silicon carbides. To evaluate the features of various chemical or non-chemical networks, a variety of topological indices are defined. In this paper, a new concept related to the degree of the graph called "bi-distance" is introduced, which is used to calculate all the additive as well as multiplicative degree-based indices for the isomer of silicon carbide, Si2C3-1[t, h]. The term "bi-distance" is derived from the concepts of degree and distance in such a way that second distance can be used to calculate degree-based topological indices.

Number theorists believe that primes play a central role in Number theory and that solving problems related to primes could lead to the resolution of many other unsolved conjectures, including the prime k-tuples conjecture. This paper aims to demonstrate the existence of this conjecture for admissible k-tuples in a positive proportion. The authors achieved this by refining the methods of “Goldston, Pintz and Yildirim” and “James Maynard” for studying bounded gaps between primes and prime k-tuples. These refinements enabled to overcome the previous limitations and restrictions and to show that for a positive proportion of admissible k-tuples, there is the existence of the prime k-tuples conjecture holding for each “k”. The significance of this result is that it is unconditional which means it is proved without assuming any form of strong conjecture like the Elliott–Halberstam conjecture

In this paper, some basic notions and facts in the b-modular space similar to those in the modular spaces as a type of generalization are given. For example, concepts of convergence, best approximate, uniformly convexity etc. And then, two results about relation between semi compactness and approximation are proved which are used to prove a theorem on the existence of best approximation for a semi-compact subset of b-modular space.

E-wallet, also referred to as digital wallet, is a software application designed to replace physical wallets, with the primary purpose of facilitating online transactions when users wish to make virtual payments. Nowadays, E-wallets are not limited to mobile applications, but they have also been extended to wearable devices, such as smartwatches, enabling users to make payments via their watches. This research study focuses on three main E-wallet service providers in Malaysia, namely TouchNGo E-wallet, Boost, and Grab pay, as they are the top three E-wallets in the country. The aim of this paper is to explore the real-world implementation of E-wallets among mobile phone users in Malaysia, employing the Technology Adoption Model as the theoretical framework. Six independent variables were identified to study the implementation of E-wallets, and a total of 500 respondents shared their opinions on retaining the usage of E-wallet in Malaysia. The data collected were analysed using SPSS for Pearson Correlation Analysis and Multiple Linear Regression. Out of the six variables, five independent variables were accepted, and one independent variable was rejected due to the greater significant level. The highest correlation coefficient falls under Business Resources with 0.704. The study delves into the implications and constraints, providing insights for the future advancement of E-wallets within the Malaysian context.

Human posture estimation is a crucial topic in the computer vision field and has become a hotspot for research in many human behaviors related work. Human pose estimation can be understood as the human key point recognition and connection problem. The paper presents an optimized symmetric spatial transformation network designed to connect with single-person pose estimation network to propose high-quality human target frames from inaccurate human bounding boxes, and introduces parametric pose non-maximal suppression to eliminate redundant pose estimation, and applies an elimination rule to eliminate similar pose to obtain unique human pose estimation results. The exploratory outcomes demonstrate the way that the proposed technique can precisely recognize the human central issues, really work on the exactness of human posture assessment, and can adjust to the intricate scenes with thick individuals and impediment. Finally, the difficulties and possible future trends are described, and the development of the field is presented.

The dependable and efficient identification of Qin seal script characters is pivotal in the discovery, preservation, and inheritance of the distinctive cultural values embodied by these artifacts. This paper uses image histograms of oriented gradients (HOG) features and an SVM model to discuss a character recognition model for identifying partial and blurred Qin seal script characters. The model achieves accurate recognition on a small, imbalanced dataset. Firstly, a dataset of Qin seal script image samples is established, and Gaussian filtering is employed to remove image noise. Subsequently, the gamma transformation algorithm adjusts the image brightness and enhances the contrast between font structures and image backgrounds. After a series of preprocessing operations, the oriented gradient histograms (HOG) features are extracted from the images. During model training, different weights are assigned to classes with varying sample quantities to address the issue of class imbalance and improve the model's classification accuracy. Results show that the model achieves an accuracy of 95.30%. This research can help historians quickly identify and extract the text content on newly discovered Qin slip cultural relics, shortening the cycle of building a historical database.

An oil spill is a leakage of pipelines, vessels, oil rigs, or tankers that leads to the release of petroleum products into the marine environment or on land that happened naturally or due to human action, which resulted in severe damages and financial loss. Satellite imagery is one of the powerful tools currently utilized for capturing and getting vital information from the Earth's surface. But the complexity and the vast amount of data make it challenging and time-consuming for humans to process. However, with the advancement of deep learning techniques, the processes are now computerized for finding vital information using real-time satellite images. This paper applied three deep-learning algorithms for satellite image classification, including ResNet50, VGG19, and InceptionV4; They were trained and tested on an open-source satellite image dataset to analyze the algorithms' efficiency and performance and correlated the classification accuracy, precisions, recall, and f1-score. The result shows that InceptionV4 gives the best classification accuracy of 97% for cloudy, desert, green areas, and water, followed by VGG19 with approximately 96% and ResNet50 with 93%. The findings proved that the InceptionV4 algorithm is suitable for classifying oil spills and no spill with satellite images on a validated dataset.

Alzheimer's disease (AD) increasingly affects the elderly and is a major killer of those 65 and over. Different deep-learning methods are used for automatic diagnosis, yet they have some limitations. Deep Learning is one of the modern methods that were used to detect and classify a medical image because of the ability of deep Learning to extract the features of images automatically. However, there are still limitations to using deep learning to accurately classify medical images because extracting the fine edges of medical images is sometimes considered difficult, and some distortion in the images. Therefore, this research aims to develop A Computer-Aided Brain Diagnosis (CABD) system that can tell if a brain scan exhibits indications of Alzheimer's disease. The system employs MRI and feature extraction methods to categorize images. This paper adopts the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset includes functional MRI and Positron-Version Tomography scans for Alzheimer's patient identification, which were produced for people with Alzheimer's as well as typical individuals. The proposed technique uses MRI brain scans to discover and categorize traits utilizing the Histogram Features Extraction (HFE) technique to be combined with the Canny edge to representing the input image of the Convolutional Neural Networks (CNN) classification. This strategy keeps track of their instances of gradient orientation in an image. The experimental result provided an accuracy of 97.7% for classifying ADNI images.

Recommendation systems are now being used to address the problem of excess information in several sectors such as entertainment, social networking, and e-commerce. Although conventional methods to recommendation systems have achieved significant success in providing item suggestions, they still face many challenges, including the cold start problem and data sparsity. Numerous recommendation models have been created in order to address these difficulties. Nevertheless, including user or item-specific information has the potential to enhance the performance of recommendations. The ConvFM model is a novel convolutional neural network architecture that combines the capabilities of deep learning for feature extraction with the effectiveness of factorization machines for recommendation tasks. The present work introduces a novel hybrid deep factorization machine (FM) model, referred to as ConvFM. The ConvFM model use a combination of feature extraction and convolutional neural networks (CNNs) to extract features from both individuals and things, namely movies. Following this, the proposed model employs a methodology known as factorization machines, which use the FM algorithm. The focus of the CNN is on the extraction of features, which has resulted in a notable improvement in performance. In order to enhance the accuracy of predictions and address the challenges posed by sparsity, the proposed model incorporates both the extracted attributes and explicit interactions between items and users. This paper presents the experimental procedures and outcomes conducted on the Movie Lens dataset. In this discussion, we engage in an analysis of our research outcomes followed by provide recommendations for further action.

Microservice architecture offers many advantages, especially for business applications, due to its flexibility, expandability, and loosely coupled structure for ease of maintenance. However, there are several disadvantages that stem from the features of microservices, such as the fact that microservices are independent in nature can hinder meaningful communication and make data synchronization more challenging. This paper addresses the issues by proposing a containerized microservices in an asynchronous event-driven architecture. This architecture encloses microservices in containers and implements an event manager to keep track of all the events in an event log to reduce errors in the application. Experiment results show a decline in response time compared to two other benchmark architectures, as well as a lessening in error rate.

Data-driven models perform poorly on part-of-speech tagging problems with the square Hmong language, a low-resource corpus. This paper designs a weight evaluation function to reduce the influence of unknown words. It proposes an improved harmony search algorithm utilizing the roulette and local evaluation strategies for handling the square Hmong part-of-speech tagging problem. The experiment shows that the average accuracy of the proposed model is 6%, 8% more than HMM and BiLSTM-CRF models, respectively. Meanwhile, the average F1 of the proposed model is also 6%, 3% more than HMM and BiLSTM-CRF models, respectively.

Regression testing is a crucial phase in the software development lifecycle that makes sure that new changes/updates in the software system don’t introduce defects or don’t affect adversely the existing functionalities. However, as the software systems grow in complexity, the number of test cases in regression suite can become large which results into more testing time and resource consumption. In addition, the presence of redundant and faulty test cases may affect the efficiency of the regression testing process. Therefore, this paper presents a new Hybrid Framework to Exclude Similar & Faulty Test Cases in Regression Testing (ETCPM) that utilizes automated code analysis techniques and historical test execution data to identity and exclude redundant, similar and faulty test cases from the given regression suite. Our experimental results clearly show the benefits of the ETCPM framework in terms of reduction in the testing time, optimization of the resource allocation, and improvement in the overall quality of regression test suite. ETCPM enables software development teams to achieve faster and reliable regression testing by intelligent exclusion of similar and fault test cases, which yields in reduction in the software delivery cycles and better end user satisfaction.

The field of autonomous robotic systems has advanced tremendously in the last few years, allowing them to perform complicated tasks in various contexts. One of the most important and useful applications of guide robots is the support of the blind. The successful implementation of this study requires a more accurate and powerful self-localization system for guide robots in indoor environments. This paper proposes a self-localization system for guide robots. To successfully implement this study, images were collected from the perspective of a robot inside a room, and a deep learning system such as a convolutional neural network (CNN) was used. An image-based self-localization guide robot image-classification system delivers a more accurate solution for indoor robot navigation. The more accurate solution of the guide robotic system opens a new window of the self-localization system and solves the more complex problem of indoor robot navigation. It makes a reliable interface between humans and robots. This study successfully demonstrated how a robot finds its initial position inside a room. A deep learning system, such as a convolutional neural network, trains the self-localization system as an image classification problem. The robot was placed inside the room to collect images using a panoramic camera. Two datasets were created from the room images based on the height above and below the chest. The above-mentioned method achieved a localization accuracy of 98.98%.

F index is a connected graph, sum of the cubes of the vertex degrees. The forgotten topological index has been designed to be employed in the examination of drug molecular structures, which is extremely useful for pharmaceutical and medical experts in understanding the biological activities. Among all the topological indices, the forgotten index is based on degree connectivity on bonds. This paper characterized the forgotten index of union of graphs, join graphs, limits on trees and its complements, and accuracy is measured. Co-index values are analyzed for the various molecular structure of chemical compounds

The use of real-time machine learning to optimize passport control procedures at airports can greatly improve both the efficiency and security of the processes. To automate and optimize these procedures, AI algorithms such as character recognition, facial recognition, predictive algorithms and automatic data processing can be implemented. The proposed method is to use the R-CNN object detection model to detect passport objects in real-time images collected by passport control cameras. This paper describes the step-by-step process of the proposed approach, which includes pre-processing, training and testing the R-CNN model, integrating it into the passport control system, and evaluating its accuracy and speed for efficient passenger flow management at international airports. The implementation of this method has shown superior performance to previous methods in terms of reducing errors, delays and associated costs

An automatic text summarization system mimics how humans summarize by picking the most ‎significant sentences in a source text. However, the complexities of the Arabic language have become ‎challenging to obtain information quickly and effectively. The main disadvantage of the ‎traditional approaches is that they are strictly constrained (especially for the Arabic language) by the ‎accuracy of sentence feature ‎functions, weighting schemes, ‎and similarity calculations. On the other hand, the meta-heuristic search approaches have a feature that tolerates imprecision, gets ‎prohibited results, and is not strictly bound by the above ‎restrictions. This ‎paper used the Gravitational Optimization Algorithm (GOA), a powerful metaheuristic ‎approach ‎based on the law of ‎gravity, to address the challenge of extractive summarizing Arabic texts. The objective function of the GOA algorithm is derived based on sentence significance, such as its length, ‎similarity degree, position, statistical term frequency, and named entity ownership. Essex Arabic ‎Summaries Corpus (EASC) was used to evaluate the proposed method and measured by the Recall-Oriented Understudy for Gisting Evaluation (ROUGE). The proposed approach achieved 68.04% Recall, ‎‎58.49% Precision, and 60.05% F1-measure using ROUGE-1, higher than standard summarizers and metaheuristic approaches

This paper discusses estimating the two scale parameters of Exponential-Rayleigh distribution for singly type one censored data which is one of the most important Rights censored data, using the maximum likelihood estimation method (MLEM) which is one of the most popular and widely used classic methods, based on an iterative procedure such as the Newton-Raphson to find estimated values for these two scale parameters by using real data for COVID-19 was taken from the Iraqi Ministry of Health and Environment, AL-Karkh General Hospital. The duration of the study was in the interval 4/5/2020 until 31/8/2020 equivalent to 120 days, where the number of patients who entered the (study) hospital with sample size is (n=785). The number of patients who died during the period of study was (m=88). And the number of patients who survived during the study period was (n-m=697), then utilized one of the most important non-parametric tests which is the Chi-square test to determine if the sample (data) corresponded with the Exponential-Rayleigh distribution (ER). then, after estimating the parameters of ER distribution for singly type-I censoring data, compute the survival function, hazard function, and probability density function.