International Journal on Artificial Intelligence Tools

The growing popularity of computing applications has sparked the interest of students in computer programming languages. Minor mistakes are prevalent while writing small code blocks due to the coder’s lack of knowledge and carelessness. Instead of merely providing syntax warnings, it would be better to offer developers with an Integrated Development Environment (IDE) that can automatically correct short code blocks containing mistakes. This makes code composition easier and more time-efficient, thus improving the efficacy of large-scale development environments. Because Python is becoming more popular, the goal of our study is to enhance the efficiency of writing Python code by offering an automatic code-correcting approach. Furthermore, automatic program evaluation has been performed to assist in the debugging of small code blocks, which will ultimately be employed in the creation of real-time computer applications. The proposed technique would be useful for new learners who wish to create small Python code blocks for ease of writing and debugging on online platforms (like edX, Coursera, and Udacity). One of the major contributions of the project is to create an erroneous dataset of Python coding that contains all potential forms of probable syntax errors. The dataset induces variety through the use of multiple coding templates and is used to train deep learning models. We used the state-of-the-art text-to-text T5 transformer network model to automatically repair and evaluate the incorrect code. The outcomes of auto-correction are examined using the ROUGE and BLEU scores, as well as accuracy. The model corrects Python code with single, double, and the multiple number of errors with greater than 80% accuracy. Similarly, the performance of the basic T5 transformer network for program auto-evaluation with and without mistakes has been examined, and the model achieves greater than 65% accuracy in both cases. The proposed T5 base transformer outperforms the SOTA auto-correction models in terms of accuracy, according to a comparison study of the proposed method with the earlier techniques for auto-correcting codes.

Agriculture not only plays a vital role in human survival but also contributes to the nation’s greater economic development. With the use of technologies like IoT, WSNs, remote sensing, camera surveillance, and many more, precision agriculture is the newest buzzword in the field of technology. Its primary goal is to lessen the labour of farmers while increasing the output of farms. Many machine learning techniques are designed to improve the productivity and quality of the crops, but the improper irrigation and disease prediction of the existing techniques leads to loss of productivity and quality. Hence, the IoT based wireless communication system is designed for smart irrigation and rice leaf prediction using ANN and ResNeXt-50 model. In this designed model, smart irrigation is controlled by collecting the temperature and moisture of the soil in the agricultural field by using the WSN. Likewise, a surveillance camera is placed in the agricultural field to capture the rice leaf to find the disease such as rice blast, leaf smut, brown spot and bacterial blight. These collected data are processed and classified for smart irrigation and rice leaf disease prediction. For evaluating the performance of both the ANN and ResNeXt-50 trained model, the performance metrics such as accuracy, sensitivity, specificity, precision, error etc. The performance metrics for the ANN and ResNeXt-50 model are 0.9427, 0.925, 0.903, 0.86, 0.0573 and 0.967, 0.935, 0.943, 0.939 and 0.033. Thus, the evaluation of the designed model results that the proposed approach is performing better compared to the current techniques.

Named Entity Recognition (NER) is an NLP field that deals with recognizing and classifying entities in written text. Most Arabic NER research studies discuss the Arabic NER challenge for the Modern Standard Arabic (MSA) language. However, the presence of dialectal Arabic textual resources in social media, blogs, TV shows, etc. is increasingly progressive. Therefore, the treatment of named entities is rapidly becoming a necessity, particularly for dialectal Arabic. In this paper, we are interested in the collection and annotation of a corpus as well as the realization of a NER system for Tunisian Arabic (TA), named TUNER. To the best of the researchers’ knowledge, this is the first study that uses the suggested method for this purpose. In the present study, we adopt a hybrid method based on a Bi-LSTM-CRF model and a rule-based method. The proposed TUNER system yields an F-measure of 91.43%. This is an interesting improvement over comparable related work dialectal Arabic NER systems.

Skin cancer is a perilous kind of cancer caused by damaged DNA and it leads to death. This damaged DNA causes uncontrolled proliferation of cells. Even though, the image analysis of lesions is highly difficult due to light reflections from skin surface, fluctuations at color lighting, variety of lesions’ forms and sizes in skin cancer. Because of these issues, automatic recognition of skin cancer accurateness is decreased. Therefore, a Graph Convolutional Neural Network (GCNN) by ResNet 152 Transfer Learning Architype optimized with Chameleon Swarm Optimization Algorithm (GCNN-ResNet 152 TL-CSOA) is proposed at this manuscript for enhancing skin cancer detection with classification in medical image processing. Initially, the input images are taken from International Skin Imaging Collaboration (ISIC) of dermoscopic skin cancer imagery data set. Afterward, the input images are pre-processed utilizing trilateral filter method for removing noise. The pre-processed output is supplied to the process of feature extraction. Here, image features, like morphologic, gray scale statistic and Haralick texture features are extracted by Gray-Level Co-Occurrence Matrix window adaptive approach (GLCM-WAA) technique. After that, the GCNN-ResNet 152 TL classifies the skin cancer images into Actinic Keratosis, Basal Cell Carcinoma, Malignant Melanoma and Squamous Cell Carcinoma. Additionally, GCNN-ResNet 152 TL weight parameters is tuned by Chameleon Swarm Optimization Algorithm (CSOA). The simulation process is executed at Python tool. From simulation, the proposed approach attains 23.34%, 12.03%, 21.42% improved accuracy and 18.23%, 21.23%, 14.56% higher sensitivity compared with existing approaches.

Text classification involves organizing textual information into predefined classes, a task which is particularly useful in domains like sentiment analysis, spam detection, and content labeling. In India, where a massive amount of information is generated daily through newspapers and social media, Hindi is one of the most widely used and spoken languages. However, there is limited research on Hindi text classification and, particularly, regarding Hindi news classification. This paper presents a research study to classify Hindi news articles published in Hindi-language newspapers in India by using and comparing various Machine Learning (ML) and Deep Learning (DL) algorithms. To prepare the textual news data for classification, pre-processing and feature engineering techniques, such as count vectorizer, Tf-Idf vectorizer and Doc2Vec, were used and applied to convert texts into vectors. This pre-processing step on the textual data was very challenging due to the presence of multimodal words, conjunctions, punctuation, and special characters in Hindi texts. The study considered Hindi news headlines from predetermined categories (Science, Sports, Entertainment and Business) and, among the different ML and DL models tested and evaluated, Linear Regression with Doc2Vec vectorizer and SGD classifier with Tf-Idf vectorizer produced best accuracies of 97.04% and 96.59%, respectively. The best performing DL model was found to be the Bi-LSTM with an accuracy of approximately 97% on the testing data.

In Internet of Things (IoT) and cloud systems, Intrusion Detection (ID) is very vital for protecting the security infrastructures. ID techniques are extensively used to detect and track malicious threats in cloud and IoT systems. In the IoT based ID, the conventional techniques work based on the manual traffic feature values that increase the complexity of the networks and achieve a limited detection rate on the larger IoT databases. For addressing the above-stated issues and achieving high classification results, an effective deep learning based ID-System (IDS) is implemented in this article. Initially, the IoT data is acquired from the NSW-NB15 and NSL-KDD databases, and then, the standard scaling normalization technique, known as Min-Max normalization, is applied to select the dominant attributes and to eliminate outliers from the acquired databases. Additionally, the optimal features are selected from the rescaled normalized data by implementing the Bat optimization algorithm. The selection of optimal features decreases the computational complexity and training time of the IDS. The chosen optimal features are passed into the DenseNet model for carrying out intrusion attack detection. Particularly, in the binary-class classification, the Bat-based DenseNet model obtained 98.89% and 98.40% of accuracy on the UNSW-NB15 and NSL-KDD databases, correspondingly. The obtained simulation results prove the higher effectiveness of the current study when it is related to the state-of-the-art classifiers.

Large and expanding cities suffer from a traffic congestion problem that harms the environment, travelers, and the economy. This paper aims to predict short term traffic congestion on a road section of expressway in Delhi city. For this purpose, we first propose a traffic congestion index based on traffic speed and flow. Clustering techniques and the Greenshield’s model were used for the derivation of the congestion index. Using this congestion index, congested time intervals of each day and each location of a weekday were identified. This study also introduces a feature series long short-term memory neural network (FSLSTMNN), which links a long short-term memory (LSTM) layer to each feature. It is trained using the many heterogeneous traffic features data collected in Delhi city for the next five minutes of traffic flow and speed prediction. FSLSTMNN achieved the good capability to learn feature series data. We also trained several traditional and deep-learning models using the same traffic data. The FSLSTMNN reduces mean absolute error 12.90% and 17.13%, respectively, in speed and traffic flow prediction compared to the second good-performance long short-term memory neural network (LSTMNN). Finally, traffic congestion is predicted classwise (light, medium, and congested) using the developed congestion index and traffic speed and flow predicted by the FSLSTMNN. Predicted results are consistent with the measured field data. Study results confirm that the developed congestion index and FSLSTMNN can be used successfully to predict traffic congestion.

Automatic and precise segmentation of lung images can assist doctors in locating and diagnosing lung lesions. However, current traditional lung CT image lesion segmentation algorithms suffer from the problem of low segmentation accuracy, while deep learning-based segmentation algorithms struggle to strike a better balance between lightweight and high accuracy. In response to this issue, a multi-scale and lightweight U-Net lung image segmentation algorithm with an attention mechanism is proposed. This algorithm introduces CA convolution after the convolution in the encoding stage to extract channel relationships and positional information from the feature maps. Furthermore, the RFB module is employed to extract features from different perspectives. Lastly, upward residual connections are introduced between the RFB modules in the encoder and decoder to enhance inter-network information interaction. Experiments conducted on the LUNA (lung nodule analysis) dataset and the COVID-QU-Ex dataset for COVID-19 pneumonia demonstrate that the proposed MSA-UNet algorithm achieves the best results in terms of Precision and Dice metrics. It outperforms mainstream models such as U-Net++ and DeeplabV3+ in terms of segmentation effectiveness and segmentation generality. The model has a floating-point operation count (FLOPs) of 18.15 G, a network parameter counts of 8.83×106, and achieves a Precision of 99.37%. The algorithm achieves a good balance between computational efficiency, model size, and segmentation accuracy.

Current state-of-the-art techniques in 2D chart analysis primarily emphasize the recognition of textual information as a means of comprehending and summarizing chart contents. However, the effective analysis and understanding of information embedded in chart images depends on accurate reverse-engineering of the behavior of depicted variables. In this paper, we propose a methodology, named Abax, as an initial study for recognizing and approximating the mathematical functions that describe the behavior of variables illustrated in chart images, particularly those containing curves. Abax is focused on approximating the values of function parameters using spatial pixel information derived from the identified keypoints of each curve. Qualitative results of the described method are presented as a proof of concept, demonstrating accurate extraction of information from fives types of functions: linear, polynomial, asymptotic, sinusoidal and arbitrary.