Fake news has eroded trust in credible news sources, driving the need for tools to verify the accuracy of circulating information. Fact verification addresses this issue by classifying claims as Supports (S), Refutes (R), or Not Enough Info (NEI) based on evidence. Neural Semantic Matching Networks (NSMN) is an algorithm designed for this purpose, but its reliance on BiLSTM has shown limitations, particularly overfitting. This study aims to enhance NSMN for fact verification through a structured framework comprising encoding, alignment, matching, and output layers. The proposed approach employed Siamese MaLSTM in the matching layer and introduced the Manhattan Fact Relatedness Score (MFRS) in the output layer, culminating in a novel algorithm called Deep One-Directional Neural Semantic Siamese Network (DOD–NSSN). Performance evaluation compared DOD–NSSN with NSMN and transformer-based algorithms (BERT, RoBERTa, XLM, XL-Net). Results demonstrated that DOD–NSSN achieved 91.86% accuracy and consistently outperformed other models, achieving over 95% accuracy across diverse topics, including sports, government, politics, health, and industry. The findings highlight the DOD–NSSN model’s capability to generalize effectively across various domains, providing a robust tool for automated fact verification.

API (Application Programming Interface) merupakan bahasa dan format pesan yang digunakan untuk berkomunikasi dengan Data Base Management System. API dapat mengintegrasikan suatu data ke aplikasi apapun dengan mudah, karena aplikasi yang di kembangkan berdasarkan API akan otomatis memiliki fitur yang di berikan oleh aplikasi tujuan, tanpa perlu menambahkan datanya secara manual, kemudahan ini bisa dicapai dengan komunikasi yang baik antar aplikasi, API dapat membangun aplikasi lintas platform dengan berbagai layanan, dan dapat meringankan beban server. PT. TKI (TOKO KESEHATAN INTI) merupakan perusahaan retail modern, dengan nama toko Inti Health Store, yang bergerak di bidang penjualan alat kesehatan, peralatan ibu dan bayi, personal care, vitamin dan suplemen kesehatan. Toko Inti Health Store yang menjual produk secara online maupun offline menimbulkan permasalahan, yakni stok barang tidak sesuai dengan kenyataan, laporan yang masih menggunakan kertas, serta belum memberikan kemudahan akses di berbagai kondisi yang membuat operasional perusahaan terhambat sesuai. Metode yang digunakan dalam penelitian ini adalah metode pengumpulan data dan pengembangan sistem Extreme Programming. Berdasarkan hasil penelitian yang telah dilakukan menyatakan bahwa penggunaan API Shopee sangat berguna dan berpengaruh dalam sinkronisasi stok di PT TKI, sehingga stok online pada platform e-commerce Shopee dan stok offline pada toko retail telah tersinkronisasi dengan baik.

Tea is one of the top ten export products sent from Indonesia to foreign countries. However, in recent years, the amount of tea leaf exports from Indonesia has decreased, although the value of the export impacts the country’s economic structure. In addition to market competition, Indonesia must maintain tea leaf production so that the increase in export decline is not significant or even increases tea leaf export production. To improve production quality and reduce production costs, early detection of tea leaf diseases is necessary. This study aims to classify tea leaf images for early detection of tea leaf disease so that appropriate treatment can be carried out early. This study compares machine learning algorithms to determine the best algorithm for detecting tea leaf diseases. The algorithms tested as performance comparisons in classifying tea leaf diseases are random forest (RF), support vector classifier (SVC), extra tree classifier (ETC), decision tree (DT), XGBoost classifier (XGB), and convolutional neural algorithms. Network (CNN). As a result, the average accuracy performance generated by ETC produces a higher value than other algorithms, i.e., getting an average accuracy performance of 77.47%. Another algorithm, SVC, has an average accuracy of 76.57%, RF of 76.12%, DT of 65.31%, XGB of 71.62%, and the lowest is CNN of 59.08%. ETC has been proven to be the most superior machine learning algorithm for detecting tea leaf diseases in this study.

Many different industries are currently making substantial use of the Internet of Things (IoT). IoT is the process through which electronic devices communicate with their surrounding virtual environment by continuously exchanging data via sensors. Due to increased IoT security concerns, digital forensic investigators now possess greater knowledge and abilities to investigate IoT devices. IoT-DigFor are required in terms of cybercrime due to the rapid growth in the number of electronic devices and the collection and consumption of enormous amounts of data. IoT systems with billions of devices have produced a significant amount of evidence, which presents a significant challenge to digital investigators and practitioners who must connect with IoT devices to conduct fast and thorough investigations into cybercrimes. This article presents detailed information about forensics in the IoT environment. The IoT forensic paradigm and the challenges that design-based security requirements and IoT system security offer for IoT-DigFor are covered in great detail at the beginning of the article.

Permasalahan sampah di Jawa Barat, khususnya Desa Manyingsal di Kabupaten Subang menjadi topik pembicaraan serius Pemerintah Provinsi Jawa Barat karena dampak negative sampah yang semakin meningkat. Penelitian ini membahas pengembangan timbangan berbasis Internet of Things (IoT) sebagai solusi untuk pemantauan dan pengelolaan sampah organik dalam konteks Smart Waste Management (SWM). Sistem yang dikembangkan mengintegrasikan teknologi sensor Load Cell, memungkinkan pemantauan real-time terhadap berat sampah organik yang dihasilkan. Implementasi dilakukan melalui platform IoT yang terhubung, memungkinkan akses dan pengelolaan data timbangan dengan mudah melalui aplikasi berbasis web. Penelitian ini bertujuan meningkatkan efisiensi pengelolaan sampah organik, sejalan dengan upaya mencapai lingkungan yang lebih bersih dan berkelanjutan. Hasil eksperimen menunjukkan bahwa timbangan berbasis IoT ini memberikan pemantauan yang akurat dan responsif terhadap perubahan kondisi sampah. Implikasi dari penelitian ini adalah penerapan solusi pintar dan terkoneksi dalam pengelolaan sampah organik, memberikan dasar untuk peningkatan keberlanjutan dalam kerangka Smart Waste Management secara menyeluruh.

Seiring dengan perkembangan teknologi informasi, media berita juga turut berkembang menyajikan informasi dalam media online. Namun, sangat disayangkan pada penyebarannya masih banyak ditemukan berita hoax atau berita palsu. Berita palsu yang paling mudah beredar adalah berita palsu tentang informasi isu-isu terkini contohnya tentang Covid-19 dan bencana alam. Agar terhindar dari berita hoax yang beredar, salah satu caranya yaitu dengan lebih teliti membaca judul berita pada situs yang terpercaya seperti Liputan6, Kompas.com, dan CNN. Dalam penelitian ini penulis mengambil topik berita hoax tentang vaksinasi, penyebaran virus Corona dan isu-isu yang memang tidak benar tentang pandemi Covid-19, tidak hanya itu untuk memprediksinya penulis juga membutuhkan berita fakta untuk bisa menjadi perbandingan antara berita palsu dengan fakta dari kasus Covid-19. Karena itu penelitian ini akan membuat model klasifikasi berita palsu virus Covid-19 dengan menerapkan algoritma Support Vector Machine (SVM). Hasil penelitian menyatakan bahwa model klasifikasi berita palsu Covid-19 dengan Algoritma Support Vector Machine (SVM) memiliki nilai akurasi 78%. Setelah uji coba model SVM terhadap dataset Covid-19, deploy model dilakukan dan diharapkan untuk masa yang akan datang masyarakat dapat mengakses situs pengecekan berita palsu. Selain mendapatkan prediksi judul berita yang dikategorikan dengan "Fake" dan "True", web juga dapat menampilkan persentase probabilitas dari prediksi yang dilakukan oleh model. Dengan adanya sistem ini, diharapkan dapat memprediksi judul berita tentang virus Covid-19 seakurat mungkin, baik berita palsu maupun berita yang berisikan fakta.

Blockchain came because of the occurrence of incredulity to single authorities by introducing the concept of network decentralization and data distribution saved in a ledger. Decentralization is used to validate discrepancies in the majority of data. The consensus mechanism collectively maintains the consistency of the ledger. A blockchain is a set of blocks containing transaction data interconnected to each other using the concept of cryptography. A mining process is an effort to add new blocks to the blockchain. The mining computer carries out the process after passing several complex mathematical problems. The fastest miner is rewarded with crypto coins. Some consensus mechanisms commonly used in blockchain are proof of work, proof of stake, practical byzantine fault tolerance, and proof of elapsed time. Blockchain network is designed and implemented in such a way that it can guarantee the security of its data, is easy to be audited, is robust to denial of service and majority attacks, and is private and confidential. The application of blockchain is not limited to finance systems; it can also be applied in health, education, supply chain, and state democracy systems.

The application of the bidirectional encoder model to detect fake news has been widely applied because of its ability to provide factual verification with good results. Good fact verification requires the most optimal model and has the best evaluation to make news readers trust the reliable and accurate verification results. In this study, we evaluated the application of a homogeneous ensemble (HE) on RoBERTa to improve the accuracy of a model. We improve the HE method using a bagging ensemble from three types of RoBERTa models. Then, each prediction is combined to build a new model called RoBERTaEns. The FEVER dataset is used to train and test our model. The experimental results showed that the proposed method, RoBERTaEns, obtained a higher accuracy value with an F1-Score of 84.2% compared to the other RoBERTa models. In addition, RoBERTaEns has a smaller margin of error compared to the other models. Thus, it proves that the application of the HE functions increases the accuracy of a model and produces better values in handling various types of fact input in each fold.

We reviewed some features of a number of fact verification techniques by comparing 3 (three) algorithms, namely BERT, RoBERTa, and Electra. These 3 (three) algorithms have different advantages, i.e., BERT and RoBERTa predict hidden words using a huge dataset, and Electra verifies facts by detecting tokens that are replaced in a text or sentence. It is necessary to find the model with a good performance evaluation value to produce the best fact verification results. The evaluation of the performance model in this study uses the F1-Score. Our experimental results show that RoBERTa achieves the best accuracy and F1-Score with a value of 95.4% and 95.3% with the parameter value of epoch of 5 (five) and a batch size of 32. The second position is occupied by BERT, with the best result of accuracy and F1-Score at the same value of 94.3% with the epoch of10 (ten) and a batch size of32. Although it provides a shorter elapsed time, unfortunately, Electra does not outperform other models in fact verification.

Malware is a severe threat that makes computer security more vulnerable. Many studies have been conducted to improve the capability of detection techniques. However, there is a lack of analysis of the current trend of IDS. This paper is about extracting and analyzing the latest detection techniques which had been conducted by various studies. This paper will also emphasize the current challenges of malware deployment from recent studies. Finally, the similarities and differences between the detection techniques will be exposed, and the issues and problems related to detection techniques will highlight as well. In the future, this paper outcome can be used to highlight the current topic addressed in malware research.

Tour guides are the critical services for the Travel Bureau. Especially for the services, they provide to tourists. So, a realtime system is needed to be able to interact between the two parties, especially regarding service records in the field and information processing for the Bureau. Based on ScienceDirect library, unfortunately, until there was no reporting system facilitate both parties and recorded in realtime. This study discusses software development solutions that receive various field notes by workers and can be directly viewed online for employers. This research is in the form of a reporting model, which is a solution for the Travel Bureau to have data and be stored electronically on the server. The system was built using a platform that is on a smartphone, so the tour guide reporting system becomes a solution for the Travel Bureau and the Tour Guide to document the trips carried out.

Pelayanan dengan menggunakan kertas dan berbasis elektornik memang memiliki dampak yang berbeda, selain memberikan kemudahan dan kecepatan, layanan dengan elektornik lebih digemari oleh generasi saat ini[1],[2],[3]. Di RW 06 Cikutra kota Bandung, peneliti dengan paltform Google Sites, membuat website RW yang mengakomodir layanan warga, antara lain administrasi, posyandu, siskamling, hingga IKM[4],[5],[6]. Khusus pada layanan posyandu, tercantum info ketahanan pangan yang bisa membantu masyarakat dalam mencegah isu stunting[7],[8],[9],[10]. Selain memberikan informasi seputar kegiatan posyandu, feature ini juga bisa menampilkan data pangan yang dihasilkan oleh warga RW 06 Cikutra. Selain itu website ini menjadi informasi perihal kekuatan dan kekurangan pangan bagi warga agar bisa saling berbagi. Kendala yang dihadapi saat melakukan uji coba dan penerapan sistem keterbatasan layanan dari Google Sites karena bersifat free, serta warga yang belum terbiasa dengan penggunaan fasilitas elektonik[1],[2],[3].

The vehicle key is a safety device for the vehicle. Most keys on vehicles today still use physical keys, and some use keyless. This study examines the use of vehicle keys that are connected to smartphones. The method used in this research is literature study and experimental study. The technology used in this research is based on Arduino, and some of them are equipped with Bluetooth modules, HC-05, and relays. This solution is an initial study of the SmartKey system concept. This SmartKey provides a function to turn on and turn off the machine. The resulting SmartKey from the results of this research will make it easier for application developers to control critical functions and be equipped with remote turning on and off methods, and developing various other features through application development. The key generated in this study can be an alternative to lock system development in conventional motor vehicles.

Irrigation is one of the backbones in the field of agriculture. The role of technology in the industrial era 4.0 has increased tremendously in irrigation management systems. Areas, limited internet access, and validation of activity reports are separate issues in monitoring the performance of irrigation field workers in real-time. Therefore, we built a reporting system that is equipped with location tracking using the Smartphone Global Positioning System (GPS) and the Web Geographic Information System (WebGIS) application. This field reporting system starts from the report input form on the Android app that detects location coordinates automatically. Reports are stored in an offline SQLite database and sent to the MySQL database server online through the data synchronisation process. From the server-side, information displayed through the WebGIS application. This field reporting is more efficient in monitoring the performance of irrigation systems in real-time.

Availability of internet access is one of the needs for tourists when traveling. Unfortunately, the availability of access is quite limited when in a tourist destination, usually Wi-Fi also generally uses a closed system that cannot be accessed by just anyone, except those who get access keys only. This paper provides a solution for the model of internet access for tourists provided by Tourism Service Providers, by utilizing drone technology as an access point. In addition, this model also provides services to track the position of tourists who spread and facilities for communication between tourists, especially for certain conditions, such as the occurrence of saturation for tourists while in one of the tourist destinations.

Bandung merupakan ibu kota provinsi Jawa Barat yang mejadi salah satu tempat tujuan untuk berwisata di indonesia. Kota terbesar di Jawa Barat ini menawarkan bayak tempat untuk berwisata ataupun berrkreasi baik itu yang berhubungan dengan alam, bahari, sejarah, kuliner, belanja, edukasi, dan lain-lain. Salah satu temapat yang sering dikunjungi wisatawan di Bandung adalah kebun Binatang, selain untuk menikmati flaura dan fauna wisata ini juga menjadi sarana edukasi. Semua informasi tersebut terdapat pada papan informasi konvensional yang berada didepan kandang atau di area satwa. Papan informasi Kebun Binatang Bandung yang masih konvensional akibatnya pada papan informasi Kebun Binatang tersebut kurang lengkap karena terbatasnya ruang yang terdapat pada Papan informasi, dan ada sebagian papan informasi yang terbengkalai, akibatnya informasi tidak dapat terlihat dengan jelas. Mengingat keberadaan Kebun Binatang Bandung yang memiliki peran penting dalam bidang pariwisata, maka dari itu perlu adanya sistem terkomputerisasi yang bisa mendukung Kebun Binatang tersebut. Diperlukan sebuah sistem informasi berbasis Android yang mampu memberikan informasi mengenai Kebun Binatang Bandung. Tujuannya agar menghasilkan informasi yang lebih cepat dan akurat demi meningkatkan jumlah pengunjung dan diharapkan masyarakat lebih mudah dan cepat mendapatkan informasi yang diinginkan. Metode yang digunakan dalam perancangan sistem ini adalah menggunakan RAD (Rapid Aplication Development) pengembangan yang digunakan untuk merancang sistem yaitu menggunakan UML (Unified Modeling Language), sedangkan untuk teknik pengumpulan data yaitu observasi, aplikasi yang dipilih dalam perancangan android ini ialah Unity dengan database Vuforia. Sistem yang dirancang adalah Augmented Reality ARZoo Berbasis Android diharapkan sesuai tujuan yaitu dapat meningkatnya wisatawan Kebun Binatang Bandung.

Virus spread increase significantly through the internet in 2017. One of the protection method is using antivirus software. The wide variety of antivirus software in the market tends to creating confusion among consumer. Selecting the right antivirus according to their needs has become difficult. This is the reason we conduct our research. We formulate a decision making model for antivirus software consumer. The model is constructed by using factor analysis and AHP method. First we spread questionnaires to consumer, then from those questionnaires we identified 16 variables that needs to be considered on selecting antivirus software. This 16 variables then divided into 5 factors by using factor analysis method in SPSS software. These five factors are security, performance, internal, time and capacity. To rank those factors we spread questionnaires to 6 IT expert then the data is analyzed using AHP method. The result is that performance factors gained the highest rank from all of the other factors. Thus, consumer can select antivirus software by judging the variables in the performance factors. Those variables are software loading speed, user friendly, no excessive memory use, thorough scanning, and scanning virus fast and accurately.

Perancangan ini dilatar belakangi oleh kondisi perkembangan ilmu teknologi yang maju pesat khususnya dibidang pencitraan digital, disini penelitian menggunakan obyek jari tangan manuisa untuk dikembangkan agar dapat menggerakan kursor tetikus. penelitian ini menggunakan metode konversi citra digital yang disebut Threshold, dan menggunakan algoritma Convexity Defect and Hull yang kemudian diterjemahkan ke dalam bahasa C# menggunakan Software Microsoft Visual Studio C# 2010 dan juga menggunakan library dari EmguCV yang di khususkan untuk pengolahan citra digital . Hasil perancangan dari sistem ini berupa aplikasi untuk menggerakan kursor tetikus, namun tidak hanya itu aplikasi ini juga dapat melakukan proses klik sama seperti fitur yang ada pada tetikus pada umumnya.

E-CRM is currently one of the major keys of a company in achieving the target of selling their products. Most companies today, used e-CRM without any consideration the effect of using e-CRM, such as information that is not right in use and is limited to general information delivery. E-CRM must be observed and monitored continuously to determine the extent of services provided to the company to users and buyers of their products. It is then, e-CRM can affect a quality of service and the net benefits obtained company is doing well or not. E-CRM in many forms in conveying information about products produced by a company, usually in the marketing of these products. The relationship between the user and the company must be closely and maintained mutual trust. The better the monitoring and delivery of their e-CRM, was influential excellent in quality of service and the net benefits obtained companies become more than without the use of e-CRM. One of the companies that implement e-CRM is PT. Garuda Indonesia. PT. Garuda Indonesia promote e-CRM in providing good quality services so as to obtain net benefits of the implementation of e-CRM.

The purpose of making a mobile-based information applications lecturer is to provide convenience for the lecturer in obtaining academic information anywhere and anytime. In addition, this application is expected to assist lecturer in academic activities such as obtaining information record lectures, see the list of students, giving a final value, obtain academic information, obtain information record lectures and dedication, and to provide complaints and suggestions to be more effective in terms of time and save more paper. This app has been demonstrated in 21 lecturer at the Sekolah Tinggi Teknologi Bandung. This app uses push notification functionality so that every user can find out the latest information about the academic information. This application is built using ndroid Studio version 2.1 with the Java programming language and XML. The end result of this research is a mobile based application that is named Sistem Informasi Dosen (SID) with the Android operating system that can be used on a minimal operating system Android version 4.0 IceCream Sandwich.