Arabic is one of the official languages recognized by the United Nations (UN) and is widely used in the middle east, and parts of Asia, Africa, and other countries. Social media activity currently dominates the textual communication on the Internet and potentially represents people’s views about specific issues. Opinion mining is an important task for understanding public opinion polarity towards an issue. Understanding public opinion leads to better decisions in many fields, such as public services and business. Language background plays a vital role in understanding opinion polarity. Variation is not only due to the vocabulary but also cultural background. The sentence is a time series signal; therefore, sequence gives a significant correlation to the meaning of the text. A recurrent neural network (RNN) is a variant of deep learning where the sequence is considered. Long short-term memory (LSTM) is an implementation of RNN with a particular gate to keep or ignore specific word signals during a sequence of inputs. Text is unstructured data, and it cannot be processed further by a machine unless an algorithm transforms the representation into a readable machine learning format as a vector of numerical values. Transformation algorithms range from the Term Frequency–Inverse Document Frequency (TF-IDF) transform to advanced word embedding. Word embedding methods include GloVe, word2vec, BERT, and fastText. This research experimented with those algorithms to perform vector transformation of the Arabic text dataset. This study implements and compares the GloVe and fastText word embedding algorithms and long short-term memory (LSTM) implemented in single-, double-, and triple-layer architectures. Finally, this research compares their accuracy for opinion mining on an Arabic dataset. It evaluates the proposed algorithm with the ASAD dataset of 55,000 annotated tweets in three classes. The dataset was augmented to achieve equal proportions of positive, negative, and neutral classes. According to the evaluation results, the triple-layer LSTM with fastText word embedding achieved the best testing accuracy, at 90.9%, surpassing all other experimental scenarios.

Object detection is an important task required in computer vision to solve many problems. This is because humans have very good performance in object detection task, compared to machines, hence the need to improve computer vision. Object detection consists of two sub tasks, namely localization of the object and classification of the object. Object detection is slow due to high computing capacity demand of both sub tasks. Consequently, segmentation and classification performance are often slow, even when deployed on high-capacity computing platforms such as CPU-GPU combinations. Edge devices are constrained by limited computational power, which results in poor object detection performance. The implementation of near-edge computing is used particularly in applications such as drone surveillance and autonomous vehicles, where real-time decision-making is essential despite the inherent limitations in computing power. Current object detection methods such as Regional Convolutional Neural Network (RCNN) and You Only Look Once (YOLO) rely on millions of weight parameters, typically stored in two, four, or eight bytes. Therefore, the algorithms need to store the weight parameters in big size of memory and when the operation of the weight parameters and the input signal are executed, longer bytes of data require higher computational load. The huge volume of operations required lead to slower computation. To address this issue, it is necessary to simplify the object detection models, through the reduction of the byte size and the number weight parameter. The challenges of implementing object detection in near edge computing devices is providing the lightweight the object detection models while maintaining the precision and accuracy. This review discusses the current state of object detection methods, object detection simplification methods including deep learning compression techniques, the previous effort undertaken research community to mitigate these challenges, and the associated limitations. This paper also discusses some simplification techniques carried out such as regional proposal network (RPN) replacement, backbone compression and head modification. Some of the object detection model simplification will target the near edge devices with Central Processing unit (CPU) and Graphical Processing Unit (GPU) through varying memory configuration and clock speed. In general, object detection model simplification will lead to an increase in speed with a consequences of mean average precision (mAP) drop. The remaining challenge is to find the best suitable model compression in order to achieve the speed and maintain high mAP.

Internet users are continually exposed to phishing as cybercrime in the 21st century. The objective of phishing is to obtain sensitive information by deceiving a target and using the information for financial gain. The information may include a login detail, password, date of birth, credit card number, bank account number, and family-related information. To acquire these details, users will be directed to fill out the information on false websites based on information from emails, adverts, text messages, or website pop-ups. Examining the website’s URL address is one method for avoiding this type of deception. Identifying the features of a phishing website URL takes specialized knowledge and investigation. Machine learning is one method that uses existing data to teach machines to distinguish between legal and phishing website URLs. In this work, we proposed a method that combines correlation and recursive feature elimination to determine which URL characteristics are useful for identifying phishing websites by gradually decreasing the number of features while maintaining accuracy value. In this paper, we use two datasets that contain 48 and 87 features. The first scenario combines power predictive score correlation and recursive feature elimination; the second scenario is the maximal information coefficient correlation and recursive feature elimination. The third scenario combines spearman correlation and recursive feature elimination. All three scenarios from the combined findings of the proposed methodologies achieve a high level of accuracy even with the smallest feature subset. For dataset 1, the accuracy value for the 10 features result is 97.06%, and for dataset 2 the accuracy value is 95.88% for 10 features.

Although batik is one of the most prestige heritage in Indonesia, many Indonesian people cannot recognize the pattern name of batik that they wear or see. Moreover, the batik varieties increase each year so batik pattern becomes harder to be identified. Based on that fact, automatic batik classification become of more importance to assist people in recognizing the batik pattern. In addition, Batik patterns are critical to being understood because there is the history behind the pattern. In order to recognize the batik pattern automatically, we implement batik classification methods using Convolutional Neural Network (CNN) that is called VGG-16 and VGG-19 and they are able to predict almost 90% correctly in classifying batik patterns. But the variation of batik images such as rotated and scaled images make the classifier cannot effectively detect the type of batik pattern. To illustrate, the batik classification accuracy becomes less than 56% when it has classified a batik pattern that is scaled 2.0. Then we train the CNN with augmented data to improve the accuracy. After all, the augmented data technique can improve the accuracy as well as 10% for rotated images or scaled images.

Edge computing, a distributed computing paradigm that places small yet capable computing devices near data sources and IoT sensors, is gaining widespread adoption in various real-world applications, such as real-time intelligent drones, autonomous vehicles, and robotics. Object detection (OD) is an essential task in computer vision. Although state-of-the-art deep learning-based OD methods achieve high detection rates, their large model size and high computational demands often hinder deployment on resource-constrained edge devices. Given their limited memory and computational power, edge devices like the Jetson Nano (J. Nano), Jetson Orin Nano (Orin Nano), and Raspberry Pi 4B (Raspi4B) require model optimization and compression techniques in order to deploy large OD models such as YOLO. YOLOv4 is a widely used OD model with a backbone for image feature extraction and a prediction layer. Originally, YOLOv4 was designed to use CSPDarkNet53 as its backbone, which requires significant computational power. In this paper, we propose replacing its backbone with a smaller model, such as MobileNetV2 and RepViT. In order to ensure the strong backbone performance, we perform knowledge distillation (KD), using CSPDarknet53 as the teacher and the smaller model as the student.We compare various KD algorithms to identify the technique that produces a smaller model with the modest accuracy drop. According to our experiments, Contrastive Representation Distillation (CRD) yields MobileNetV2 and RepViT with an acceptable accuracy drop. We consider both accuracy drop and model size to choose either MobileNetV2 or RepViT model to replace CSPDarknet53 in the modified YOLOv4 named M-YOLO-CRD and RV-YOLO-CRD. Our evaluation results demonstrate that RV-YOLO-CRD reduces 30% of model size and achieves better mean average precision (mAP) than M-YOLO-CRD. Our experiments show that the M-YOLO-CRD significantly reduces model size (from 245.5 MB to 35.76 MB) and inference time (6× faster on CPU, 4× faster on J. Nano, and 2.5× faster on Orin Nano. While the precision decreased slightly (less than 4%) , the model still performs well on edge devices. The M-YOLO-CRD achieved latency per frame at around 37 ms on Orin Nano, 168 ms on J. Nano, and 1310 ms on Raspi4B.

Proper selection of diciplines/programs of study is a vital task for student. Therefore a decission support system is highly demanded to help prospective students to decide the right choice. Considered factors in taking the programs of study selection are vary among people. Determining the best combination of atributes to achieve the best selection to support prospective students is important. We use student data and it's atributes as well as their choice as a dataset. This research implements classification algorithm and regression trees (CART). An Evaluation of CART algorithm using combination of 3,4,5 and 6 available students data atributes has been carried out. According to the experiments, 5 atributes achieve the best accuracy at 86%, while 6, 4 and 3 atributes yielded worse accuracy at 80%,70% and 56% respectively.