Applied Computational Intelligence and Soft Computing

Aspect-based sentiment analysis (ABSA) is the subfield of natural language processing that deals with essentially splitting data into aspects and finally extracting the sentiment polarity as positive, negative, or neutral. ABSA has been widely investigated and developed for many resource-rich languages such as English and French. However, little work has been done on indigenous African languages like Afaan Oromoo both at the document and sentence levels. In this paper, ABSA for Afaan Oromoo movie reviews was investigated and developed. To achieve the proposed objective, 2800 Afaan Oromoo movie reviews were collected from YouTube using YouTube Data API. Following the data preprocessing, predetermined aspects of the Afaan Oromoo movie were extracted and labeled into positive or negative aspects by domain experts. For implementation, different machine learning algorithms including random forest, logistic regression, SVM, and multinomial naïve Bayes in combination with BoW and TF-IDF were applied. To test and measure the proposed system, accuracy, precision, recall, and f1-score were used. In the case of random forest, the accuracy obtained in combination with both BoW and TF-IDF was 88%. Using the SVM, the accuracy generated with BoW and TF-IDF was 88% and 87%, respectively. Applying logistic regression, the accuracy generated with both BoW and TF-IDF was 87%. Using multinomial naïve Bayes, the accuracy generated in combination with both BoW and TF-IDF was 88%. To improve the optimal performance evaluation parameters, different hyperparameter tuning settings were applied. The implementation result shows that the optimal values of models’ performance evaluation parameters were generated using different hyperparameter tuning settings.

Sign language is a unique communication tool helping to bridge the gap between people with hearing impairments and the general public. It holds paramount importance for various communities, as it allows individuals with hearing difficulties to communicate effectively. In sign languages, there are numerous signs, each characterized by differences in hand shapes, hand positions, motions, facial expressions, and body parts used to convey specific meanings. The complexity of visual sign language recognition poses a significant challenge in the computer vision research area. This study presents an Arabic Sign Language recognition (ArSL) system that utilizes convolutional neural networks (CNNs) and several transfer learning models to automatically and accurately identify Arabic Sign Language characters. The dataset used for this study comprises 54,049 images of ArSL letters. The results of this research indicate that InceptionV3 outperformed other pretrained models, achieving a remarkable 100% accuracy score and a 0.00 loss score without overfitting. These impressive performance measures highlight the distinct capabilities of InceptionV3 in recognizing Arabic characters and underscore its robustness against overfitting. This enhances its potential for future research in the field of Arabic Sign Language recognition.

Antibiotic-resistant bacteria have proliferated at an alarming rate as a result of the extensive use of antibiotics and the paucity of new medication research. The possibility that an antibiotic-resistant bacterial infection would progress to sepsis is one of the major collateral problems affecting people with this condition. 31,000 lives were lost due to sepsis in England with costs about two billion pounds annually. This research aims to develop and evaluate several classification approaches to improve predicting sepsis and reduce the tendency of underdiagnosis in computer-aided predictive tools. This research employs medical datasets for patients diagnosed with sepsis, and it analyses the efficacy of ensemble machine learning techniques compared to nonensemble machine learning techniques and the significance of data balancing and conditional tabular generative adversarial nets for data augmentation in producing reliable diagnosis. The average F Score obtained by the nonensemble models trained in this paper is 0.83 compared to the ensemble techniques average of 0.94. Nonensemble techniques, such as Decision Tree, achieved an F score of 0.90, an AUC of 0.90, and an accuracy of 90%. Histogram-basedgradient boosting classification tree achieved an F score of 0.96, an AUC of 0.96, and an accuracy of 95%, surpassing the other models tested. Additionally, when compared to the current state-of-the-art sepsis prediction models, the models developed in this study demonstrated higher average performance in all metrics, indicating reduced bias and improved robustness through data balancing and conditional tabular generative adversarial nets for data augmentation. The study revealed that data balancing and augmentation on the ensemble machine learning algorithms boost the efficacy of clinical predictive models and can help clinics decide which data types are most important when examining patients and diagnosing sepsis early through intelligent human-machine interface.

Chronic kidney disease (CKD) is a progressive condition characterized by the gradual deterioration of kidney functions, potentially leading to kidney failure if not promptly diagnosed and treated. Machine learning (ML) algorithms have shown significant promise in disease diagnosis, but in healthcare, clinical data pose challenges: missing values, noisy inputs, and redundant features, affecting early-stage CKD prediction. Thus, this study presents a novel, fully automated machine learning approach to tackle these complexities by incorporating feature selection (FS) and feature space reduction (FSR) techniques, leading to a substantial enhancement of the model’s performance. A data balancing technique is also employed during preprocessing to address data imbalance issue that is commonly encountered in clinical contexts. Finally, for reliable CKD classification, an ensemble characteristics-based classifier is encouraged. The effectiveness of our approach is rigorously validated and assessed on multiple datasets, and the clinical relevancy of the strategy is evaluated on the real-world therapeutic data collected from Bangladeshi patients. The study establishes the dominance of adaptive boosting, logistic regression, and passive aggressive ML classifiers with 96.48% accuracy in forecasting unseen therapeutic CKD data, particularly in early-stage cases. Furthermore, the effectiveness of the FSR technique in reducing the prediction time significantly is revealed. The outstanding performance of the proposed model demonstrates its effectiveness in addressing the complexity of healthcare CKD data by incorporating the FS and FSR techniques. This highlights its potential as a promising computer-aided diagnosis tool for doctors, enabling early interventions and improving patient outcomes.

MEMS-IMUs are widely used in research, industry, and commerce. A proper calibration technique must reduce their innate errors. In this study, a turntable-based IMU calibration approach was presented. Parameters such as the bias, lever arm, and scale factor, in addition to misalignment, are included in the general nonlinear model of the IMU output. Accelerometer error parameters were estimated using the transformed unscented Kalman filter (TUKF) with triangulation algorithm is suggested for calibrating inertial measurement unit (MPU6050) three-axes accelerometer. In contrast to the present methods, the suggested method uses the gravitational signal as a constant reference and necessitates no external equipment. The technique requires that the sensor be positioned in a rough orientation and that basic rotations be adopted. This technology also offers a quicker and easier calibration. Comparing the experimental findings with other works, Allan deviation shows significant improvements for the bias instability, where a bias instability of (0.116 μg) is achieved at temperatures between (−15°C) and (80°C).

Pattern matching algorithms have gained a lot of importance in computer science, primarily because they are used in various domains such as computational biology, video retrieval, intrusion detection systems, and fraud detection. Finding one or more patterns in a given text is known as pattern matching. Two important things that are used to judge how well exact pattern matching algorithms work are the total number of attempts and the character comparisons that are made during the matching process. The primary focus of our proposed method is reducing the size of both components wherever possible. Despite sprinting, hash-based pattern matching algorithms may have hash collisions. The Efficient Hashing Method (EHM) algorithm is improved in this research. Despite the EHM algorithm’s effectiveness, it takes a lot of time in the preprocessing phase, and some hash collisions are generated. A novel hashing method has been proposed, which has reduced the preprocessing time and hash collision of the EHM algorithm. We devised the Hashing Approach for Pattern Matching (HAPM) algorithm by taking the best parts of the EHM and Quick Search (QS) algorithms and adding a way to avoid hash collisions. The preprocessing step of this algorithm combines the bad character table from the QS algorithm, the hashing strategy from the EHM algorithm, and the collision-reducing mechanism. To analyze the performance of our HAPM algorithm, we have used three types of datasets: E. coli, DNA sequences, and protein sequences. We looked at six algorithms discussed in the literature and compared our proposed method. The Hash-q with Unique FNG (HqUF) algorithm was only compared with E. coli and DNA datasets because it creates unique bits for DNA sequences. Our proposed HAPM algorithm also overcomes the problems of the HqUF algorithm. The new method beats older ones regarding average runtime, number of attempts, and character comparisons for long and short text patterns, though it did worse on some short patterns.