Telkom University

Promosi adalah suatu hal yang harus dilakukan setiap perusahaan. Hal utama dalam promosi adalah membuat pesan yang persuasif yang efektif untuk menarik perhatian konsumen. Berdasarkan fakta tersebut, saat ini instagram tidak hanya digunakan sebagai sarana pemuas kebutuhan hiburan saja, tetapi juga sebagai media sosial yang mempunyai peluang besar untuk melakukan kegiatan bisnis, menyusul kesuksesannya sebagai media sosial yang diminati oleh pengguna. Happy Go Lucky house, pelopor concept store di Indonesia yang berdiri sejak 2008 mempromosikan produknya memakai instagram, tujuan penelitian ini adalah untuk mengetahui kegiatan promosi apa saja yang dilakukan oleh Happy Go Lucky house dalam akun media sosial instagram, dan mengetahui faktor-faktor apa yang membuat instagram dipilih sebagai media promosi yang aktif. Peneliti menarik kesimpulan bahwa Happy Go Lucky house melakukan pemanfaatan instagram dengan baik, dilihat dari kegiatan promosi yang dilakukan sangat beragam dan juga dapat memanfaatkan berbagai fitur yang tersedia. Abstract Promotion is an important thing to be done by a company. The key point in promotion is creating effective and persuasive message to attract buyers' attention. In line with that fact, instagram nowadays is used not only to fulfill users' entertainment needs, but also to be a social media with good opportunities to support business activities, following it's success to be a well known social media with lot of users. Happy Go Lucky house, pioneer of concept store fashion in Indonesia that established since 2008 have been using social media instagram as their product promotion platform. The objective of this research is to find out what kind of promotion activities doing by Happy Go Lucky house in social media account instagram. And also to find out the reasons why instagram is chosen as their active media promotion. The author concludes that Happy Go Lucky house doing well in using instagram, seen from their various promotions and also their ability of utilizing available features on it.

This paper considers the use of Synthetic Minority Oversampling Technique (SMOTE), Principal Component Analysis (PCA), and Ensemble Feature Selection (EFS) to improve the performance of AdaBoost-based Intrusion Detection System (IDS) on the latest and challenging CIC IDS 2017 Dataset [1]. Previous research [1] has proposed the use of AdaBoost classifier to cope with the new dataset. However, due to several problems such as imbalance of training data and inappropriate selection of classification methods, the performance is still inferior. In this research, we aim at constructing an improvement performance intrusion detection approach to handle the imbalance of training data, SMOTE is selected to tackle the problem. Moreover, Principal Component Analysis (PCA) and Ensemble Feature Selection (EFS) are applied as the feature selection to select important attributes from the new dataset. The evaluation results show that the proposed AdaBoost classifier using PCA and SMOTE yields Area Under the Receiver Operating Characteristic curve (AUROC) of 92% and the AdaBoost classifier using EFS and SMOTE produces an accuracy, precision, recall, and F1 Score of 81.83 %, 81.83%, 100%, and 90.01% respectively.

Process mining techniques can be used to analyse business processes using the data logged during their execution. These techniques are leveraged in a wide range of domains, including healthcare, where it focuses mainly on the analysis of diagnostic, treatment, and organisational processes. Despite the huge amount of data generated in hospitals by staff and machinery involved in healthcare processes, there is no evidence of a systematic uptake of process mining beyond targeted case studies in a research context. When developing and using process mining in healthcare, distinguishing characteristics of healthcare processes such as their variability and patient-centred focus require targeted attention. Against this background, the Process-Oriented Data Science in Healthcare Alliance has been established to propagate the research and application of techniques targeting the data-driven improvement of healthcare processes. This paper, an initiative of the alliance, presents the distinguishing characteristics of the healthcare domain that need to be considered to successfully use process mining, as well as open challenges that need to be addressed by the community in the future.

This paper examines the calculation of the similarity between words in English using word representation techniques. Word2Vec is a model used in this paper to represent words into vector form. The model in this study was formed using the 320,000 articles in the English Wikipedia as the corpus and then Cosine Similarity calculation method is used to determine the similarity value. This model then tested by the test set gold standard WordSim-353 as many as 353 pairs of words and SimLex-999 as many as 999 pairs of words, which have been labelled with similarity values according to human judgment. Pearson Correlation was used to find out the accuracy of the correlation. The results of the correlation from this study are 0.665 for WordSim-353 and 0.284 for SimLex-999 using the Windows size 9 and 300 vector dimension configurations.

BACKGROUND: Invasive fungal infections are found most frequently in immunosuppressed and critically ill hospitalized patients. Antifungal therapy is often required for long periods. Safety data from the clinical development program of the triazole antifungal agent, posaconazole, were analyzed. METHODS: A total of 428 patients with refractory invasive fungal infections (n = 362) or febrile neutropenia (n = 66) received posaconazole in 2 phase II/III open-label clinical trials. Also, 109 of these patients received posaconazole therapy for > or = 6 months. Incidences of treatment-emergent, treatment-related, and serious adverse events and abnormal laboratory parameters were recorded during these studies. RESULTS: Treatment-emergent, treatment-related adverse events were reported in 38% of the overall patient population. The most common treatment-related adverse events were nausea (8%) and vomiting (6%). Treatment-related serious adverse events occurred in 8% of patients. Low rates of treatment-related corrected QT interval and/or QT interval prolongation (1%) and elevation of hepatic enzymes (2%) were reported as adverse events. Treatment-emergent, treatment-related adverse events occurred at similar rates in patients who received posaconazole therapy for < 6 months and > or = 6 months. CONCLUSIONS: Prolonged posaconazole treatment was associated with a generally favorable safety profile in seriously ill patients with refractory invasive fungal infections. Long-term therapy did not increase the risk of any individual adverse event, and no unique adverse event was observed with longer exposure to posaconazole.

Toxicity prediction is a critical step in the drug discovery process that helps identify and prioritize compounds with the greatest potential for safe and effective use in humans, while also reducing the risk of costly late-stage failures. It is estimated that over 30% of drug candidates are discarded owing to toxicity. Recently, artificial intelligence (AI) has been used to improve drug toxicity prediction as it provides more accurate and efficient methods for identifying the potentially toxic effects of new compounds before they are tested in human clinical trials, thus saving time and money. In this review, we present an overview of recent advances in AI-based drug toxicity prediction, including the use of various machine learning algorithms and deep learning architectures, of six major toxicity properties and Tox21 assay end points. Additionally, we provide a list of public data sources and useful toxicity prediction tools for the research community and highlight the challenges that must be addressed to enhance model performance. Finally, we discuss future perspectives for AI-based drug toxicity prediction. This review can aid researchers in understanding toxicity prediction and pave the way for new methods of drug discovery.

Increasing environmental awareness among societies is motivating consumers to use green cosmetic products. Green skincare products are the fastest growing sector in the worldwide market compared with other green cosmetic products. However, compared with general cosmetic products, the market share of green cosmetic products in Indonesia is relatively low. The present research investigated consumers’ purchasing intentions toward green skincare products in Indonesia using the pro-environmental reasoned action (PERA) model. A total of 251 female consumers participated in this study. Structural equation modeling was conducted to reveal the relationships between the five factors in the PERA model. The results indicated that perceived authority support (PAS) has a positive effect on perceived environmental concern (PEC). PAS and PEC have positive effects on attitude (AT) and subjective norms (SN), and AT and SN have positive effects on behavioral intention (BI) to purchase green skincare products, with the key factor being attitude. The PERA model was able to describe 62.6% of the BI to purchase green skincare products. Green skincare companies are recommended to produce more green skincare products and market the products by involving public figures and emphasizing the green attributes. Furthermore, we recommend that green skincare companies produce quality and sustainable products using quality processes, and be involved in pro-environmental activity to increase consumer attention to the green skincare products.

Awal virus corona ditemukan ketika ada penduduk kota Wuhan Cina terjangkit.Penyakit disebabkan oleh virus SARS-CoV-2, sebelumnya orang beranggapan gejala yang dialami sebagai flu biasa, sampai WHO mendeklarasikan pandemi COVID-19. Sampai tanggal 26 Mei 2020, ada 5.406.282 kasus, termasuk 343.562 kematian. Penelitian menggunakan metode mixed methods, dengan melakukan analisa statistik parametris dan non parametris dilanjutkan deskriptif kualitatif. Penelitian di kampus Telkom University dan UIN SGD Bandung menunjukkan sekitar 60.5 % mahasiswa siap beradaptasi dengan penggunaan teknologi pembelajaran perkuliahan online tetapi sekitar 59.5 % keberatan atas tugas yang diberikan dosen yang berakibat tingkat stress mahasiswa sekitar 60 %. Kalau hal ini dibiarkan terus akan berakibat fatal dalam perkembangan kejiwaan mahasiswa, dan sebanyak 92 % mahasiswa memilih dan lebih suka perkuliahan tatap muka di kelas di banding perkuliahan online. Sehingga penelitian ini ada hubungan yang erat antara perkuliahan online dengan sikap mental mahasiswa. Kata kunci: Teknologi pembelajaran, kuliah online, COVD-19, stres, kejiwaan

Amidst the rapid advancements in the digital landscape, the convergence of digitization and cyber threats presents new challenges for organizational security. This article presents a comprehensive framework that aims to shape the future of cyber security. This framework responds to the complexities of modern cyber threats and provides guidance to organizations to enhance their resilience. The primary focus lies in the integration of capabilities with resilience. By combining these elements into cyber security practices, organizations can improve their ability to predict, mitigate, respond to, and recover from cyber disasters. This article emphasizes the importance of organizational leadership, accountability, and innovation in achieving cyber resilience. As cyber threat challenges continue to evolve, this framework offers strategic guidance to address the intricate dynamics between digitization and cyber security, moving towards a safer and more robust digital environment in the future.

Covid-19 has had a significant impact on the disruption of the global economic sector, including for startup businesses. This encourages entrepreneurs to carry out a continuous innovation process to become more ambidextrous and continue to innovate in an effort to futureproof their business. The paper aims to provide a business resilience framework by exploring capability (innovation ambidexterity, dynamic capability, and technology capability), behavior (agile leadership), and knowledge (knowledge stock) in startup businesses. This study uses a literature review synthesis to gain a greater understanding of startup resilience and its implementation. This study also uses a case study approach in building a framework by obtaining data from semi-structured interviews with three startups owners in Indonesia. This preliminary research has identified four propositions that will be used to develop questionnaires and data collection instruments. Thus, this study provides new insights on how startups can overcome contradictory pressures for business resilience in anticipating, dealing with, and emerging from business turbulence due to the Covid-19 pandemic by considering the factors proposed in this study. The implications and recommendations of this study are also discussed in detail.

This article aims to provide a review of existing research on the use of OpenAI ChatGPT in education using bibliometric analysis and systematic literature review. We explored published articles to observe the leading contributors to this field, the important subtopics, and the potential study in the future. We discovered that there is already a rise in the quantity of articles published on this subject between 2022 and 2023. We also map the research clusters using network analysis. The results obtained found a total of 93 articles. The analysis conclude that keywords such as “challenge,” “teaching,” and “knowledge,” have not been thoroughly researched This article contributes to the literature discussing the use of artificial intelligence in education and can be useful for academics and policymakers in education.

People use social media as a means to express their thoughts, interests, and opinions on various things. Thousands of submissions occur every day on every social media. Everyone can express their opinions through social media freely. These opinions contain positive, negative and neutral sentiments on a topic. The case study taken by researchers is the Anti-LGBT campaign in Indonesia. The case was taken because the Anti-LGBT campaign was widely discussed by the Indonesian people on Twitter’s social media. If you want to know the tendency of public comments on the Anti-LGBT campaign in Indonesia, is it positive, negative, or neutral, then a sentiment analysis is conducted. The algorithm used in conducting sentiment analysis is Naïve Bayes because it has a high degree of accuracy in classifying sentiment analysis. The stages in conducting sentiment analysis in this study are preprocessing data, processing data, classification, and evaluation. The sentiment analysis obtained in this study shows that Twitter users in Indonesia give more neutral comments. In this study, an accuracy of 86.43% was obtained from testing data using Naïve Bayes Algorithm in RapidMiner tools, where the accuracy is higher than the other algorithms, Decision Tree and Random Forest which is 82.91%.

Purpose Women entrepreneurship has been growing and contributing significantly to economic activities, and it may also reduce unemployment, especially in developing countries. Many women entrepreneurs have begun to experience problems, including within their socio-cultural environment, in the beginning of or when they run their businesses. Among those developing countries, Indonesia has been recognized as having diverse ethnic groups, traditions, religions and languages. The purpose of this paper is to analyse how the socio-cultural environment affects women entrepreneurs in Indonesia. Design/methodology/approach This study aims at exploring the impact of the socio-cultural environment on entrepreneurial behavior, including the involvement of women in entrepreneurial activities in Indonesia as a multicultural country. A theoretical framework is empirically tested to identify the impact of the socio-culture environment on behavior and on women entrepreneurial activity through an integrated analysis. Findings A quantitative method with a causal descriptive approach is used in this study. The data are analyzed by using a descriptive statistics with the structural equation modeling technique. This study is intended to focus on women entrepreneurs in micro, small and medium enterprises in Bandung, Indonesia. A total of 210 women entrepreneurs have participated in this study. Practical implications include useful information for women entrepreneurs to overcome the impact of the socio-cultural environment in their entrepreneurial activities, and suggest insights for future research. Originality/value The development of women entrepreneurship in emerging economies may continuously face challenges, particularly in countries with multicultural attributes.

Penelitian ini bertujuan untuk menguji pengaruh Ukuran Perusahaan, Umur Perusahaan, Leverage, dan Profitabilitas terhadap Manajemen Laba pada Perusahaan Pertambangan yang terdaftar di Bursa Efek Indonesia tahun 2014-2016. Data yang digunakan dalam penelitian ini diperoleh dari data laporan keuangan. Populasi dalam penelitian ini adalah sektor Industri Pertambangan yang terdaftar di BEI. Teknik pemilihan sampel yang digunakan yaitu purposive sampling dan diperoleh 17 perusahaan dengan periode penelitian 2014-2016. Metode analisis data dalam penelitian ini adalah analisis regresi data panel. Hasil penelitian menunjukkan bahwa secara simultan Ukuran Perusahaan, Umur Perusahaan, Leverage, dan Profitabilitas berpengaruh signifikan terhadap Manajemen Laba. Secara parsial, Ukuran Perusahaan dan Profitabilitas tidak berpengaruh signifikan terhadap Manajemen Laba, sedangkan Umur Perusahaan dan Leverage berpengaruh positif dan signifikan terhadap Manajemen Laba.Kata Kunci: Leverage; Manajemen Laba; Profitabilitas; Ukuran Perusahaan, Umur Perusahaan.

) of 0.98675, a mean absolute percentage error (MAPE) of 6.635%, and a root mean squared error (RMSE) of 0.03902. Compared to empirical formulas, which are often limited to a fixed range of slopes, the XGBoost model is applicable over a broader range of beach slopes and incident wave amplitudes.•The optimized XGBoost method is a feasible alternative to existing empirical formulas and classical numerical models for predicting wave run-up.•Hyperparameter tuning is performed using the grid search method, resulting in a highly accurate machine-learning model.•Our findings indicate that the XGBoost method is more applicable than empirical formulas and more efficient than numerical models.

Perkembangan komunikasi pemasaran saat ini tidak hanya dilakukan secara konvensional saja.Pemasar kini juga memanfaatkan media baru seperti Internet sebagai alternatif untuk melakukan pendekatan kepada calon konsumen.Pemasaran Digital adalah suatu kegiatan pemasaran yang menggunakan internet dan teknologi informasi untuk memperluas dan meningkatkan fungsi marketing tradisional. Media sosial dengan segala kelebihannya dapat membantu dalam proses komunikasi pemasaran. Dalam menjalankan komunikasi pemasaran, perusahaan harus memiliki strategi supaya segala rencana yang ditentukan sebelumnya dapat tercapai. Strategi yang baik akan memberikan keuntungan bagi perusahaan sebagai terwujudnya tujuan dari perusahaan tersebut. Penelitian ini membahas tentang strategi pemanfaatan Instagram sebagai media komunikasi pemasaran digital yang dilakukan oleh Dino Donuts.Metode yang digunakan pada penelitian ini adalah metode deskriptif kualitatif. Selain itu, penelitian ini juga menggunakan teknik wawancara mendalam dengan nara sumber, studi literatur dan dokumentasi. Berdasarkan hasil penelitian dan pembahasan, diketahui bahwa perencanaan pemanfaatan Instagram yang Dino Donuts lakukan adalah dengan menganalisis masalah, menganalisis khalayak, menentukan tujuan, pemilihan media dan saluran komunikasi, dan mengembangkan rencana atau kegiatan untuk pencapaian tujuan. Pelaksanaan pemanfaatan Instagram sebagai media komunikasi pemasaran digital yang dilakukan oleh Dino Donuts adalah dengan memanfaatkan fitur foto dan video, comment , caption , location, hashtag, tagging serta Instagram ads untuk social media maintenance , juga followers dan like untuk social media endorsement.Evaluasi pemanfaatan Instagram adalah hasil penjualan yang meningkat dan berhasil membuka cabang toko dan gerai yang tersebar di Bandung, Jakarta, Bekasi dan Bogor.

&lt;span&gt;The imbalanced data problems in data mining are common nowadays, which occur due to skewed nature of data. These problems impact the classification process negatively in machine learning process. In such problems, classes have different ratios of specimens in which a large number of specimens belong to one class and the other class has fewer specimens that is usually an essential class, but unfortunately misclassified by many classifiers. So far, significant research is performed to address the imbalanced data problems by implementing different techniques and approaches. In this research, a comprehensive survey is performed to identify the challenges of handling imbalanced class problems during classification process using machine learning algorithms. We discuss the issues of classifiers which endorse bias for majority class and ignore the minority class. Furthermore, the viable solutions and potential future directions are provided to handle the problems&lt;em&gt;.&lt;/em&gt;&lt;/span&gt;

Developing a prediction model from risk factors can provide an efficient method to recognize breast cancer. Machine learning (ML) algorithms have been applied to increase the efficiency of diagnosis at the early stage. This paper studies a support vector machine (SVM) combined with an extremely randomized trees classifier (extra-trees) to provide a diagnosis of breast cancer at the early stage based on risk factors. The extra-trees classifier was used to remove irrelevant features, while SVM was utilized to diagnose the breast cancer status. A breast cancer dataset consisting of 116 subjects was utilized by machine learning models to predict breast cancer, while the stratified 10-fold cross-validation was employed for the model evaluation. Our proposed combined SVM and extra-trees model reached the highest accuracy up to 80.23%, which was significantly better than the other ML model. The experimental results demonstrated that by applying extra-trees-based feature selection, the average ML prediction accuracy was improved by up to 7.29% as contrasted to ML without the feature selection method. Our proposed model is expected to increase the efficiency of breast cancer diagnosis based on risk factors. In addition, we presented the proposed prediction model that could be employed for web-based breast cancer prediction. The proposed model is expected to improve diagnostic decision-support systems by predicting breast cancer disease accurately.

K-Nearest Neighbor (KNN) is a method applied in classifying objects based on learning data that is closest to the object based on comparison between previous and current data. In the learning process, KNN calculates the distance of the nearest neighbor by applying the euclidean distance formula, while in other methods, optimization has been done on the distance formula by comparing it with the other similar in order to get optimal results. This study will discuss the calculation of the euclidean distance formula in KNN compared with the normalized euclidean distance, manhattan and normalized manhattan to achieve optimization results or optimal value in finding the distance of the nearest neighbor.

Imbalanced data typically refers to a condition in which several data samples in a certain problem is not equally distributed, thereby leading to the underrepresentation of one or more classes in the dataset. These underrepresented classes are referred to as a minority, while the overrepresented ones are called the majority. The unequal distribution of data leads to the machine's inability to carry out predictive accuracy in determining the minority classes, thereby causing various costs of classification errors. Currently, the standard framework used to solve the unequal distribution of imbalanced data learning is the Synthetic Minority Oversampling Technique (SMOTE). However, SMOTE can produce synthetic minority data samples considered as noise, which is also part of the majority classes. Therefore, this study aims to improve SMOTE to identify the noise from synthetic minority data produced in handling imbalanced data by adding the Local Outlier Factor (LOF). The proposed method is called SMOTE-LOF, and the experiment was carried out using imbalanced datasets with the results compared with the performance of the SMOTE. The results showed that SMOTE-LOF produces better accuracy and f-measure than the SMOTE. In a dataset with a large number of data examples and a smaller imbalance ratio, the SMOTE-LOF approach also produced a better AUC than the SMOTE. However, for a dataset with a smaller number of data samples, the SMOTE's AUC result is arguably better at handling imbalanced data. Therefore, future research needs to be carried out using different datasets with combinations varying from the number of data samples and the imbalanced ratio.