Search

Social media especially Twitter has been used by corporation or organization as an effective tool to interact and communicate with the consumers. Holywings is one of the popular restaurants in Indonesia that use social media as a tool to promote and disseminate information regarding their products and services. However, one of their promotional items has gone viral and invited public protests which turned into a trending topic on Twitter for a couple of weeks. Holywings allegedly improperly promoted their products by using the most honorable names, “Muhammad” and “Maria”. Social network analysis of Twitter data is conducted to identify and examine information circulating among the users, which leads to wider public attention and law enforcement. In this study, we focused on the conversation about Holywings on Twitter from 24 June to 31 July 2022. The analysis was carried out using Python to retrieve data and Gephi software to visualize the interactions and the intensity of the network group in viewing the spread of information. The findings reveal the centrality account that caused the news to go viral are the CNN Indonesia (@CNNIndonesia) news media account and Haris Pertama (@knpiharis), with a centrality of 0.161 and 0.282, respectively. There are also 121 groups involved in the conversation with modularity of 0.821.

Facial recognition is a part of Computer Vision that is used to get facial coordinates from an image. Many algorithms have been developed to support Facial Detection such as Cascade Face Detection using Haar-Like features and AdaBoost to classify its Cascade and Convolutional Neural Network (CNN). Face recognition in this study uses the Deep Convolutional Neural Network (DCNN) method, and the output of this method is the measurement value of the face. In the model training process, Triplet Loss from Triplet Network Deep Metric Learning is used to get good face grouping results. The value of this face measurement will then be measured using the Euclidean distance calculation to determine the similarity of the input face from the dataset. This Research is using 6 images of Government officers in Indonesia to determine the accuracy of the model when there is a new picture of these officers inputted into the training machine. The result provides a 94% accuracy level with a variety of face positions and levels of brightness.

Sexual harassment is defined as giving sexual attention both verbally, either in speech or writing, and physically to victims who are predominantly women, On July 13, 2022, there was a tweet featuring a video of sexual harassment that made it trend in various countries. The video irritated Twitter users and made various comments resulting in various sentiments that can be analyzed using sentiment analysis. The purpose of this study is to see what the public thinks about the sexual harassment case of Brazilian anesthesiologist. Besides the sentiment analysis, another aim of this study is to see how objective are those sentiments based on their polarity. This study uses a comparison of two methods in sentiment analysis, namely Multi-Layer Perceptron Classifier and Random Forest, and labeling automatically using TextBlob. This results in 94.44% accuracy, 94.44% precision, 92% recall and 93% f1_score. For MLP Classifier and accuracy 96.42%, precision 94.44%, recall 96.66% and f1_score 95.56% for Random Forest. Sentiment polarity score from the TextBlob is -0.5 and subjectivity is 0.4 which indicates that most statements are negative and subjective score is 0.4, which means those sentiments are subjective in nature.

Word embedding is an efficient feature representation that carries semantic and syntactic information. Word embedding works as a word level that treats words as minor independent entity units and cannot handle words that are not in the training corpus. One solution is to generate embedding from more minor parts of words such as morphemes. Morphemes are the smallest part of a word linguistic that has meaning in the grammatical unit of languages. This study aims to build a morpheme embedding model for Bahasa Indonesia (in English: Indonesian Language) in sort: Bahasa. However, there were many morphological rules in Bahasa, such as inflectional and derivational affixes. This implies that all rules in word segmentation will increase the computational complexity. Moreover, the rules were not regular and similar for all words in Bahasa. Therefore, this study modified a Byte Pair Embedding (BPE) algorithm to generate morpheme embedding appropriate to the morphology of Bahasa. The study implemented a simple method by filtering the BPE segmentation results with the list of Bahasa’s morphemes. This process has proven to anticipate the limitation of a conventional BPE algorithm that produces intermediate junk tokens that are not meaningful. Based on three evaluation scenarios, the model in the study can handle OOV and carry semantic and syntactic information in the embedding value of the words.

Wireless sensor network is a network consisting of many sensor nodes that function to scan certain phenomena around it. WSN has quite a large problem in the form of delay and data loss which results in low WSN performance. This study aims to improve WSN performance by developing a cluster-based routing protocol. The cluster formation is carried out in several stages. The first is the formation of the cluster head which is the channel reference to be used by node members by means of probability calculations. The second determines the closest node using the Euclidean approach when looking for the closest member of the node to the cluster head. The third is determination of the node members by means of single linkage grouping by looking for proximity to CH. The performance of the proposed MCCH method is then tested and evaluated using QoS parameters. The results of this research evaluation use QoS parameters for testing the MCCH method, channel 1 throughput 508.165, channel 2 throughput 255.5661, channel 3 throughput 479.8289, channel 4 throughput 646.5618.

Cervical cancer is the fourth most prevalent disease in women. Accurate and timely cancer detection can save lives. Automatic and reliable cervical cancer detection methods can be devised through the accurate segmentation and classification of Pap smear cell images. This paper presents an approach to whole cervical cell segmentation using a mask regional convolutional neural network (Mask R-CNN) and classifies this using a smaller Visual Geometry Group-like Network (VGG-like Net). ResNet10 is used to make full use of spatial information and prior knowledge as the backbone of the Mask R-CNN. We evaluate our proposed method on the Herlev Pap Smear dataset. In the segmentation phase, when Mask R-CNN is applied on the whole cell, it outperforms the previous segmentation method in precision (0.92±0.06), recall (0.91±0.05) and ZSI (0.91±0.04). In the classification phase, VGG-like Net is applied on the whole segmented cell and yields a sensitivity score of more than 96% with low standard deviation (±2.8%) for the binary classification problem and yields a higher result of more than 95% with low standard deviation (maximum 4.2% in accuracy measurement) for the 7-class problem in terms of sensitivity, specificity, accuracy, h-mean, and F1 score.

In real-life applications, electroencephalogram (EEG) signals for mental stress recognition require a conventional wearable device. This, in turn, requires an efficient number of EEG channels and an optimal feature set. This study aims to identify an optimal feature subset that can discriminate mental stress states while enhancing the overall classification performance. We extracted multi-domain features within the time domain, frequency domain, time-frequency domain, and network connectivity features to form a prominent feature vector space for stress. We then proposed a hybrid feature selection (FS) method using minimum redundancy maximum relevance with particle swarm optimization and support vector machines (mRMR-PSO-SVM) to select the optimal feature subset. The performance of the proposed method is evaluated and verified using four datasets, namely EDMSS, DEAP, SEED, and EDPMSC. To further consolidate, the effectiveness of the proposed method is compared with that of the state-of-the-art metaheuristic methods. The proposed model significantly reduced the features vector space by an average of 70% compared with the state-of-the-art methods while significantly increasing overall detection performance.

Exposure to mental stress for long period leads to serious accidents and health problems. To avoid negative consequences on health and safety, it is very important to detect mental stress at its early stages, i.e., when it is still limited to acute or episodic stress. In this study, we developed an experimental protocol to induce two different levels of stress by utilizing a mental arithmetic task with time pressure and negative feedback as the stressors. We assessed the levels of stress on 22 healthy subjects using frontal electroencephalogram (EEG) signals, salivary alpha-amylase level (AAL), and multiple machine learning (ML) classifiers. The EEG signals were analyzed using a fusion of functional connectivity networks estimated by the Phase Locking Value (PLV) and temporal and spectral domain features. A total of 210 different features were extracted from all domains. Only the optimum multi-domain features were used for classification. We then quantified stress levels using statistical analysis and seven ML classifiers. Our result showed that the AAL level was significantly increased (p < 0.01) under stress condition in all subjects. Likewise, the functional connectivity network demonstrated a significant decrease under stress, p < 0.05. Moreover, we achieved the highest stress classification accuracy of 93.2% using the Support Vector Machine (SVM) classifier. Other classifiers produced relatively similar results.

The electrical energy produced by solar panel depends on the light intensity falling on the panel, but this process is prone to disturbances from external factors. Unfortunately, models of online solar panel disturbance diagnosis have not been widely developed. This research proposes a model of fog computing using fuzzy rule-based algorithm is capable of automatic monitoring and diagnosing factors affecting solar panel efficiency. Data from physical parameter of sensors are acquired by the System on Chip (SoC) Wi-Fi microcontroller and sent to the fog server via a Wi-Fi gateway. The fuzzy rule-based algorithm consists of investigation rules showing the relationships among efficiency, light intensity, output electrical power, temperature, and humidity. Output of fog network computing is sent to the cloud server and serves as information for users of this investigation system. The fog network system is able to improve cloud performance, in terms of the transmission time has increased performance from 246.1 to 27.9 ms. In general, this system is able to improve relative efficiency of solar panel by 2.1%, compared to solar panels not equipped with this instrument. In order to obtain accurate investigation results, detailed conditions of all possible events in the field are required.