Jurnal Pekommas
Not a member yet
    263 research outputs found

    Tinjauan Realitas Virtual dan Game Serius dalam Terapi Perilaku Kognitif untuk Gangguan Kecemasan Sosial

    No full text
    This literature review discusses efforts to enhance cognitive behavioral therapy in addressing social phobia, such as social anxiety disorder, by utilizing serious games and virtual reality exposure therapy. In the worldwide context of the COVID-19 outbreak, conventional cognitive behavioral therapy faces significant challenges, prompting practitioners and researchers to seek innovative e solutions. During the conducted literature review, several research articles were identified that explore the utilization of virtual reality exposure therapy and serious games within the stages of cognitive behavioral therapy. Using the PICOC method and software such as Publish or Perish, Zotero, and VOSViewer, 30 journal articles have been obtained, indicating that virtual reality exposure therapy and serious games can enhance the effectiveness of cognitive behavioral therapy. However, there are clear signs suggesting that integrating virtual reality (VR) technology and serious games on smartphones into the cognitive behavioral therapy process could offer a promising avenue for new research. This approach may help address the challenges brought about by the effects of the COVID-19 pandemic on people with social anxiety disorder, particularly in Indonesia. Although further research and therapy adaptation according to the cultural context in Indonesia are needed, this development offers new research opportunities as an alternative therapeutic approach with significant advancements in addressing social anxiety disorder.Tinjauan literatur ini membahas upaya untuk meningkatkan terapi perilaku kognitif dalam menangani fobia sosial, seperti gangguan kecemasan sosial, dengan memanfaatkan permainan serius dan terapi paparan realitas virtual. Dalam konteks global wabah COVID-19, terapi perilaku kognitif konvensional menghadapi tantangan yang signifikan, mendorong para praktisi dan peneliti untuk mencari solusi inovatif. Selama tinjauan literatur yang dilakukan, beberapa artikel penelitian telah teridentifikasi meneliti pemanfaatan terapi paparan realitas virtual dan permainan serius dalam tahapan terapi perilaku kognitif. Dengan menggunakan metode PICOC dan perangkat lunak seperti Publish or Perish, Zotero, dan VOSViewer, telah diperoleh 30 artikel jurnal yang menunjukkan bahwa terapi paparan realitas virtual dan permainan serius dapat meningkatkan efektivitas terapi perilaku kognitif. Namun, terdapat bukti yang signifikan yang menyarankan bahwa mengintegrasikan teknologi realitas virtual dan permainan serius di smartphone ke dalam proses terapi perilaku kognitif dapat menjadi peluang penelitian yang menjanjikan. Pendekatan ini dapat membantu mengatasi tantangan yang ditimbulkan oleh dampak pandemi COVID-19 terhadap orang dengan gangguan kecemasan sosial, khususnya di Indonesia. Meskipun penelitian lebih lanjut dan adaptasi terapi sesuai dengan konteks budaya di Indonesia diperlukan, pengembangan ini menawarkan peluang penelitian baru sebagai pendekatan terapeutik alternatif dengan kemajuan signifikan dalam menangani gangguan kecemasan sosia

    Pengembangan Aplikasi berbasis Android untuk Mengenali Jenis Lesi Kulit Menggunakan Convolutional Neural Network

    No full text
    Skin lesions are skin abnormalities or disorders in the form of changes, damage, abnormal growth of the skin, such as changes in texture, color, appearance of lumps and spots on the skin. This disease certainly disrupts people\u27s activities and behavior every day because of the reactions it causes, such as sensations of itching, pain, stinging and excessive heat. However, knowledge of the types of skin lesions by the lay public is still lacking and a system is needed that can provide information regarding primary skin lesions. Image processing as part of machine learning can recognize types of primary skin lesions through applications that use Convolutional Neural Network (CNN). This method can perform good feature extraction and classification, so it is very suitable for image detection. Research was carried out on 4 classes of lesions, namely macular, urticarial, popular and vesicular. Based on the test results with the CNN model, it was found that the average accuracy value was 95% with the calculation of values in the macular class with precision 91%, recall 100%, f-1 score 95%, urticaria class with precision 100%, recall 91%, f-1 score 95%, papule class with precision 98%, recall 93%, f-1 score 96% and vesicular class with precision 93%, recall 99%, f-1 score 96%.Lesi kulit merupakan kelainan atau gangguan kulit berupa perubahan, kerusakan, pertumbuhan yang abnormal terhadap kulit, seperti perubahan tekstur, warna, munculnya benjolan dan bintik pada kulit. Penyakit ini tentu mengganggu aktivitas dan perilaku orang setiap hari karena reaksi yang ditimbulkan, seperti sensasi gatal, nyerih, perih dan panas yang berlebihan. Akan tetapi pengetahuan akan jenis-jenis lesi kulit oleh masyarakat awam masih kurang dan diperlukan sebuah sistem yang mampu memberikan informasi terkait lesi kulit primer. Pengolahan citra sebagai bagian dari machine learning dapat mengenali jenis-jenis lesi kulit primer melalui aplikasi yang menggunakan Convolutional Neural Network (CNN). Metode ini mampu melakukan ekstraksi fitur dan klasifikasi yang baik sehingga sangat cocok dimanfaatkan untuk pendeteksian gambar. Penelitihan dilakukan terhadap 4 kelas lesi, yakni makula, urtikaria, papula dan vesikular. Berdasarkan hasil pengujian dengan model CNN didapati nilai rata-rata akurasi, yaitu sebesar 95% dengan perhitungan nilai pada kelas makula dengan presicion 91%, recall 100%, f-1 score  95%, kelas urtikaria dengan precision 100%, recall 91%, f-1 score 95%, kelas papula dengan precision 98%, recall 93%, f-1 score 96% dan kelas vesikular dengan  precision 93%, recall 99%, f-1 score 96%

    Optimalisasi Klasifikasi Support Vector Machine dengan SMOTE: Studi Kasus Ulasan Pengguna Aplikasi Alfagift

    No full text
    Support Vector Machine (SVM) is a supervised learning algorithm that works by classifying based on classes that refer to patterns resulting from the training process. SVM has several commonly and popularly used kernels, one of which is the linear kernel. The weakness of SVM is in the "parameter selection" and its performance tends to be poor in the case of unbalanced datasets. The purpose of this study is to overcome the weaknesses of the SVM algorithm with the proposed method. This research uses a linear kernel with feature extraction that is Word2Vec with Skip-gram model, and in handling the data imbalance problem using SMOTE (oversampling) technique. The results showed that the unbalanced dataset produced an accuracy of 90% and the balanced dataset (SMOTE) produced an accuracy of 92%, so the SMOTE oversampling technique was proven to increase the accuracy results by 2%.Support Vector Machine (SVM) adalah algoritma supervised learning yang bekerja dengan mengklasifikasi berdasarkan kelas yang mengacu pada pola hasil dari proses pelatihan. SVM memiliki beberapa kernel yang umum dan populer digunakan salah satunya adalah kernel linear. Kelemahan SVM adalah dalam “pemilihan parameter” dan performanya cenderung buruk pada kasus dataset yang tidak seimbang. Tujuan penelitian ini adalah untuk mengatasi kelemahan dari algoritma SVM dengan metode yang diusulkanPenelitian ini menggunakan kernel linear dengan ekstraksi fiturnya yaitu Word2Vec dengan model Skip-gram, dan dalam menangani masalah ketidakseimbangan data menggunakan teknik SMOTE (oversampling). Hasil penelitian menunjukkan bahwa dataset yang tidak seimbang menghasilkan akurasi sebesar 90% dan dataset yang seimbang (SMOTE) menghasilkan akurasi sebesar 92%, sehingga teknik oversampling SMOTE terbukti meningkatkan hasil akurasinya sebesar 2%.  

    Optimasi Klasifikasi Sentimen pada Komentar Online menggunakan Multinomial Naïve Bayes dan Ekstraksi Fitur TF-IDF serta N-grams

    No full text
    The Naïve Bayes (NB) algorithm is a classifier method that calculates simple probabilities and it is suitable for text classification in the context of sentiment analysis. The classic variant of NB is Multinomial Naïve Bayes (MNB). The weakness of the MNB algorithm is the assumption of feature independence. This research uses a dataset of comments and reviews from various online platforms. This study uses the proposed method to handle the weakness of the MNB algorithm, namely the use of TF-IDF feature extraction and N-grams (1-gram to 5-gram), and the use of Chi-Square feature selection, as well as handling dataset imbalance using SMOTE (oversampling and undersampling method). The results of this study show that the use of pentagram (5-gram) with data that has been oversampled by SMOTE produces the highest accuracy value of 94% and an Area Under Curve (AUC) value of 100%Algoritma Naïve Bayes (NB) merupakan metode pengklasifikasi yang menghitung probabilitas sederhana dan cocok digunakan untuk klasifikasi teks salah satunya dalam konteks analisis sentimen. Varian klasik NB adalah Multinomial Naïve Bayes (MNB). Kelemahan algoritma MNB adalah asumsi independensi terhadap fitur. Penelitian ini menggunakan dataset komentar dan ulasan dari berbagai platform online. Penelitian ini menggunakan metode yang diusulkan dalam menangani kelemahan dari algoritma MNB yaitu penggunaan ekstraksi fitur TF-IDF dan N-grams (1-gram sampai 5-gram), dan penggunaan seleksi fitur Chi-Square, serta menangani ketidakseimbangan dataset menggunakan SMOTE (metode oversampling dan undersampling). Hasil penelitian ini menunjukkan bahwa penggunaan pentagram (5-gram) dengan data yang telah dilakukan oversampling SMOTE menghasilkan nilai akurasi tertinggi sebesar 94% dan nilai Area Under Curve (AUC) sebesar 100%

    Kepemimpinan Transformasional, Keamanan Psikologis, dan Kompetensi TIK: Pengaruhnya terhadap Kinerja Karyawan

    No full text
    In the growing digital era, transformational leadership has become one of the key factors in improving employee performance. It motivates employees to achieve organizational goals and creates a psychologically safe environment, where employees feel valued and supported. This study aims to examine the influence of transformational leadership and psychological safety on employee performance, by exploring the mediating role of ICT competence in Subang Regency MSMEs. This study employs a quantitative approach utilizing SEM-PLS methodology to explore the interrelationships among relevant variables. The research was conducted on 55 SMEs, using an online questionnaire as the data collection tool. This study emphasizes that ICT competence acts as a crucial mediating factor in the relationship between transformational leadership and psychological safety on employee performance in MSMEs in Subang Regency. The analysis results show that transformational leadership and psychological safety have a positive and significant impact on employee performance, which is enhanced by ICT competence. Transformational leadership improves employee performance by strengthening technical skills, technology knowledge, and the ability to adapt to new technologies. Similarly, psychological safety, supports employee performance through increased ICT competence, which facilitates productivity, work quality, and innovation.Dalam era digital, kepemimpinan transformasional menjadi kunci dalam meningkatkan kinerja karyawan dengan memotivasi mereka untuk mencapai tujuan organisasi dan menciptakan lingkungan kerja yang aman secara psikologis. Penelitian ini mengkaji pengaruh kepemimpinan transformasional dan keamanan psikologis terhadap kinerja karyawan di UMKM Kabupaten Subang, dengan kompetensi TIK sebagai variabel mediasi. Menggunakan pendekatan kuantitatif dan metodologi SEM-PLS, data dikumpulkan dari 55 responden melalui kuesioner daring. Hasil penelitian menunjukkan bahwa kepemimpinan transformasional dan keamanan psikologis berdampak positif dan signifikan terhadap kinerja karyawan. Kompetensi TIK berperan penting dalam memperkuat dampak tersebut, dengan meningkatkan keterampilan teknis, pengetahuan teknologi, dan kemampuan beradaptasi dengan teknologi baru. Hal ini juga memfasilitasi peningkatan produktivitas, kualitas kerja, dan inovasi di kalangan karyawan UMKM

    Hubungan Literasi Digital, Paparan Video Deepfake yang Dihasilkan AI, dan Kemampuan untuk Mengidentifikasi Deepfake pada Generasi X

    No full text
    The study explores the relationship between digital literacy, exposure to AI-generated deepfake videos, and the ability to identify deepfakes by Generation X in Indonesia who are currently between the ages of 43 and 58. It also analyzes the impact of deepfake identification capabilities on the cognitive, affective, and behavioral aspects of internet users. Through a survey involving 199 respondents taken from a total population of 42 million Generation X internet users in Indonesia, it applied a random sampling method. The sample size was determined by the Slovin formula with a confidence level of 90% and a margin of error of 7.1%. The descriptive analysis shows a moderate level of digital literacy and relatively low exposure to deepfakes. However, the ability to identify deepfakes was found to be low. The results of inferential statistical analysis show that digital literacy and exposure to deepfakes do not have a significant influence on the ability to identify deepfakes. Additionally, the ability to identify deepfakes does not significantly affect cognition, compassion, or behavior. While digital literacy is important, these findings reinforce the assumptions of Generation Theory and Media Dependency Theory. Additionally, it suggests that specific training on media manipulation technologies is needed to improve deepfake detection capabilities. This research implies that efforts to improve digital literacy should be expanded, including technical skills and critical thinking relevant to manipulative media such as deepfakes.Studi ini mengeksplorasi hubungan literasi digital, paparan video deepfake yang dihasilkan AI, dan kemampuan untuk mengidentifikasi deepfake oleh Generasi X di Indonesia yang saat ini berusia antara 43 hingga 58 tahun. Penelitian ini juga menganalisis dampak kemampuan identifikasi deepfake pada aspek kognitif, afektif, dan perilaku pengguna internet. Melalui survei yang melibatkan 199 responden yang diambil dari total populasi 42 juta pengguna internet Generasi X di Indonesia, studi ini menggunakan metode sampling acak. Ukuran sampel ditentukan dengan Rumus Slovin dengan tingkat kepercayaan 90% dan margin of error sebesar 7,1%. Analisis deskriptif menunjukkan tingkat literasi digital yang moderat dan paparan deepfake yang relatif rendah. Namun, kemampuan untuk mengidentifikasi deepfake ditemukan rendah. Hasil analisis statistik inferensial menunjukkan bahwa literasi digital dan paparan deepfake tidak memiliki pengaruh yang signifikan terhadap kemampuan mengidentifikasi deepfake. Selain itu, kemampuan untuk mengidentifikasi deepfake tidak secara signifikan memengaruhi kognisi, kasih sayang, atau perilaku. Meskipun literasi digital itu penting, temuan ini menguatkan asumsi Teori Generasi dan Teori Ketergantungan Media. Hasil ini juga menunjukkan bahwa pelatihan khusus tentang teknologi manipulasi media diperlukan untuk meningkatkan kemampuan deteksi deepfake. Penelitian ini menyiratkan bahwa upaya peningkatan literasi digital harus diperluas, termasuk keterampilan teknis dan pemikiran kritis yang relevan dengan media manipulatif seperti deepfake

    Sistem Deteksi Intrusi Hybrid dan Mitigasi Kerentanan Infrastruktur Jaringan Menggunakan Teknik Active Response (XDR) Wazuh dan Suricata

    No full text
    The complexity of cyber threats against the network infrastructure of companies, educational institutions, and government makes protecting network infrastructure a top priority. Router and server devices are highly vulnerable to various types of cyber threats, requiring comprehensive detection and response solutions. This research will implement an intrusion detection system by integrating SIEM technology and Wazuh XDR (Extended Detection and Response). This system analyzes index pattern data from Wazuh agent devices to detect and respond to attacks using the XDR active response firewall. The testing was conducted MikroTik RouterOS, Ubuntu Server 20.04 as Wazuh agent to test reconnaissance attacks, brute force and DoS attacks. The results of the research show Nmap and brute force attacks were successfully detected by Wazuh manager and blocked the attacker IP malicious through active response. Detection of brute force attacks showed an increase in traffic of up to 60 Kbps and CPU usage reached 100%, then decreased after the active response firewall was activated. Authentication failure reached 2198 times in the first hour of the brute force attack. CPU usage increased from 20% to 85% during the attack and decreased to 15% after the active response firewall was activated. DoS attacks, on MikroTik experienced an increase in CPU usage of up to 61% and memory of 67%. After activating the active response firewall, CPU usage decreased to 3%. Traffic on the MikroTik interface increased to 3.3 Mbps during the attack, then decreased to 1 Kbps after the firewall was activated  Kompleksitas ancaman siber pada infrastruktur jaringan perusahaan, institusi pendidikan, dan pemerintah menjadikan perlindungan infrastruktur jaringan sebagai prioritas utama. Berbagai perangkat router dan server sangat rentan terhadap berbagai jenis ancaman siber, sehingga memerlukan solusi deteksi dan respons yang komprehensif. Penelitian ini akan mengimplementasikan sistem deteksi intrusi dengan mengintegrasikan teknologi SIEM dan (Extended Detection and Response) XDR Wazuh. Sistem ini menganalisis data index pattern dari perangkat Wazuh agent untuk mendeteksi dan merespons serangan menggunakan firewall active response XDR. Pengujian dilakukan pada perangkat MikroTik Router, ubuntu server untuk menguji serangan reconnaissance attack, brute force dan DoS. Hasil penelitian menunjukkan serangan Nmap dan brute force berhasil dideteksi oleh Wazuh manager dan memblokir IP penyerang melalui active response. Pendeteksian serangan brute force menunjukkan peningkatan traffic hingga 60 Kbps dan penggunaan CPU mencapai 100%, kemudian terjadi penurunan setelah firewall active response diaktifkan. Authentication failure mencapai 2198 kali dalam satu jam pertama serangan brute force. Penggunaan CPU meningkat dari 20% hingga 85% selama serangan dan menurun menjadi 15% setelah firewall active response diaktifkan. Serangan DoS, pada MikroTik mengalami peningkatan penggunaan CPU hingga 89% dan memori 56.32%. Setelah aktivasi firewall active response, penggunaan CPU menurun menjadi 3%. Traffic pada interface MikroTik meningkat hingga 3.3 Mbps selama serangan, kemudian menurun menjadi 1 Kbps setelah firewall diaktifka

    Transformative online learning post-pandemic: challenges, opportunities, and future trends

    No full text
    The Covid-19 pandemic forced a swift and unprecedented transition to online learning in the education sector. This research aims to comprehensively analyze the impact of the pandemic on the educational landscape and investigate how online learning has transformed. This research is grounded in a mixed-methods approach. Quantitative data, including educational institution surveys and student feedback, were collected to gauge the effectiveness of online learning implementation. Qualitative methods such as interviews with educators were employed to gain deeper insights into the experiences and perceptions surrounding the adoption of online learning. The main result of this study indicates that the pandemic has acted as a catalyst for the transformation of education, pushing institutions to embrace online learning technologies and pedagogies on an unprecedented scale. Issues of digital accessibility, pedagogical adaptation, and technological infrastructure also created numerous opportunities to enhance flexibility, inclusivity, and learner-centered approaches. The research concluded that online learning will likely remain integral to education beyond the pandemic. Future trends suggest the convergence of augmented reality, artificial intelligence, and personalized learning, promising to revolutionize the educational landscape further. Academically, this article contributes to the education field by providing valuable insights into the transformative potential of online learning in a post-pandemic context

    Penerapan Algoritma Certainty Factor pada Metode Case-Based Reasoning untuk Sistem Pakar Deteksi Stunting

    No full text
    Stunting is a severe problem that significantly impacts future generations\u27 growth and the quality of Human Resources (HR). In addition to the under-five age factor, stunting is also influenced by several interrelated factors. This research aims to apply the Certainty Factor algorithm in an expert system to detect stunting using the Case-Based Reasoning Method. The application of the CF algorithm by utilizing expert judgment has successfully strengthened the CBR method steps by calculating the similarity level. The results of the User Acceptance Test by 25 respondents showed an approval rate of 85%. If interpreted using the user approval range, these results are 81% - 100%, with a very high level of agreement. Based on calculating risky and safe stunting example cases, the CBR Method shows a similarity rate of 29.26% and 70.73%, respectively. Furthermore, safe stunting cases were analyzed using the CF algorithm with a confidence ratio of 91%.Stunting adalah masalah serius yang berdampak besar pada pertumbuhan generasi mendatang dan kualitas Sumber Daya Manusia (SDM). Selain faktor usia balita, stunting juga dipengaruhi oleh sejumlah faktor yang saling terkait. Tujuan dari penelitian ini adalah menerapkan algoritma Certainty Factor dalam sistem pakar untuk mendeteksi stunting secara dini dengan menggunakan Metode Case-Based Reasoning. Penerapan algoritma CF dengan memanfaatkan penilaian dari pakar telah berhasil memperkuat langkah-langkah dalam metode CBR dengan menghitung tingkat kemiripan. Hasil dari uji penerimaan pengguna (User Acceptance Test) oleh 25 responden menunjukkan tingkat persetujuan sebesar 85%. Jika diinterpretasikan menggunakan rentang persetujuan pengguna, hasil tersebut berada dalam kisaran 81% - 100% dengan tingkat kesetujuan yang sangat tinggi. Berdasarkan perhitungan kasus contoh stunting yang berisiko dan aman, Metode CBR menunjukkan tingkat kemiripan sebesar 29,26% dan 70,73% masing-masing. Selanjutnya, contoh kasus stunting yang aman dianalisis menggunakan algoritma CF dengan tingkat keyakinan (confidence ratio) sebesar 91%

    Tindak Tutur Ilokusi Penjual Pakaian Dalam Wanita Saat Live Di Tiktok Shop

    No full text
    An illocutionary speech act is an utterance uttered by the speaker with a specific purpose. This research aims to identify the illocutionary speech acts of women\u27s underwear sellers when live on TikTok Shop and to recapitulate what illocutionary speech acts are uttered by women\u27s underwear sellers when live on TikTok Shop and their functions. The method used in this research is qualitative. The research data is the sentences that women\u27s underwear sellers spoken during live on TikTok Shop. The data source comes from live video recordings of women\u27s underwear sellers on TikTok Shop. The research data was analyzed using J.R. Searle’s speech act theory. The research results show that assertive, directive, commissive, expressive, and declarative speech acts were found in the speech of women\u27s underwear sellers while live on TikTok Shop. Of all the speech acts, the most frequently used is assertive speech acts, followed by directive and commissive speech acts.Tindak tutur ilokusi merupakan suatu tuturan yang diucapkan oleh penuturnya dengan suatu tujuan tertentu. Penelitian ini bertujuan untuk mengidentifikasi tindak tutur ilokusi penjual pakaian dalam wanita saat live di TikTok Shop serta merekapitulasi tindak tutur ilokusi apa yang paling banyak dituturkan penjual pakaian dalam wanita saat live di TikTok Shop beserta fungsinya. Metode yang digunakan dalam penelitian ini adalah metode kualitatif. Data penelitian berupa kalimat yang diucapkan oleh penjual pakaian dalam wanita saat Live di TikTok Shop. Sumber data berasal dari rekaman video live penjual pakaian dalam wanita di TikTok Shop. Data penelitian dianalisis menggunakan teori tindak tutur dari J.R. Searle. Hasil penelitian menunjukkan bahwa ditemukan tindak tutur asertif, direktif, komisif, ekspresif, dan deklaratif pada tuturan penjual pakaian dalam wanita saat live di TikTok Shop. Dari semua tindak tutur yang digunakan tersebut, yang paling banyak digunakan adalah tindak tutur asertif, disusul dengan tindak tutur direktif, dan tindak tutur komisif

    149

    full texts

    263

    metadata records
    Updated in last 30 days.
    Jurnal Pekommas
    Access Repository Dashboard
    Do you manage Open Research Online? Become a CORE Member to access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard! 👇