Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
Evaluasi Pengaruh Parameter TIM Berdasarkan Multirate Terhadap Konsumsi Energi Jaringan IEEE 802.11ah
Get PDFWLAN IEEE 802.11ah is wireless standard technology which potentially used for IoT networking to provide longer range transmission than WPAN and LPWAN. MAC layer IEEE 802.11ah introduces TIM segmentation scheme that provides effective management toward STA in large amount to make the energy consumption efficiently. STA is organized in hierarchical structure that allows TIM segmentation to reduce the length of frame beacon contains TIM. In case there’s no segmentation in a network with many STA, the TIM would be longer and requires all STA to wake-up receiving beacon TIM including STA without downlink data. This research intends to evaluate and analyze the TIM optimal parameters. Those are Page Period, Page Slice Length and Page Slice Count toward IEEE 802.11ah energy efficiency based on multirate using simulator NS-3 implemented on IEEE 802.11ah. As the result of STA experiment shows that Non-TIM is only optimal on sleep duration while TIM is optimal on energy consumption and delay packet. In the experiment of impact of STA/Slot amount based on Page Slice Length shows that sleep duration and energy consumption is optimal depends on the amount of the STA/Slot and data rate used while the optimal packet delay varies for each Page Slice Length.
WLAN IEEE 802.11ah merupakan standar teknologi jaringan nirkabel baru yang potensial digunakan untuk jaringan IoT karena mampu menyediakan jangkauan transmisi lebih jauh dari WPAN dan LPWAN. Untuk mengefisienkan konsumsi energi pada WLAN 802.11ah, lapisan MAC memperkenalkan skema segmentasi TIM yang memungkinkan manajemen secara efektif terhadap STA dalam jumlah besar agar konsumsi energi menjadi efisien. STA diorganisasikan dalam struktur hierarkis yang memungkinkan segmentasi TIM untuk mengurangi panjang frame beacon yang mengandung TIM. Jika tanpa segmentasi, dalam jaringan dengan jumlah STA yang banyak maka TIM akan sangat panjang sehingga mengakibatkan semua STA perlu wake-up untuk menerima beacon TIM termasuk STA yang tidak memiliki data downlink sehingga terjadi pemborosan energi. Penelitian ini bertujuan untuk mengevaluasi dan menganalisis parameter TIM optimal, yaitu Page Period, Page Slice Length dan Page Slice Count terhadap efisiensi energi IEEE 802.11ah berdasarkan multirate yang pengembangannya menggunakan simulator NS-3 yang dapat diimplementasi pada IEEE 802.11ah. Perhitungan berdasarkan multirate penting dilakukan karena setiap data rate memiliki jarak jangkau, durasi sleep dan delay packet yang berbeda-beda sehingga mempengaruhi konsumsi energi IEEE 802.11ah. Berdasarkan pengujian terhadap STA yang berbasis multirate menunjukkan bahwa Non-TIM hanya optimal pada durasi sleep, sedangkan TIM optimal pada konsumsi energi dan delay packet. Pada pengujian pengaruh jumlah STA/Slot berdasarkan Page Slice Length dan multirate menunjukkan bahwa durasi sleep dan konsumsi energi optimal tergantung jumlah STA/Slot dan data rate yang digunakan, sementara delay packet akan optimal secara berbeda pada tiap-tiap Page Slice Length
The Hybrid Recommender System of the Indonesian Online Market Products using IMDb weight rating and TF-IDF
Get PDFToday, consumers are faced with an abundance of information on the internet; accordingly, it is hard for them to reach the vital information they need. One of the reasonable solutions in modern society is implementing information filtering. Some researchers implemented a recommender system as filtering to increase customers’ experience in social media and e-commerce. This research focuses on the combination of two methods in the recommender system, that is, demographic and content-based filtering, commonly it is called hybrid filtering. In this research, item products are collected using the data crawling method from the big three e-commerce in Indonesia (Shopee, Tokopedia, and Bukalapak). This experiment has been implemented in the web application using the Flask framework to generate products’ recommended items. This research employs the IMDb weight rating formula to get the best score lists and TF-IDF with Cosine similarity to create the similarity between products to produce related items. Today, consumers are faced with an abundance of information on the internet; accordingly, it is hard for them to reach the vital information they need. One of the reasonable solutions in modern society is implementing information filtering. Some researchers implemented a recommender system as filtering to increase customers’ experience in social media and e-commerce. This research focuses on the combination of two methods in the recommender system, that is, demographic and content-based filtering, commonly it is called hybrid filtering. In this research, item products are collected using the data crawling method from the big three e-commerce in Indonesia (Shopee, Tokopedia, and Bukalapak). This experiment has been implemented in the web application using the Flask framework to generate products’ recommended items. This research employs the IMDb weight rating formula to get the best score lists and TF-IDF with Cosine similarity to create the similarity between products to produce related items.  
Analisis Metode Representasi Teks Untuk Deteksi Interelasi Kitab Hadis: Systematic Literature Review
Get PDFHadith is the second source of reference for Islamic law after the Qur'an, which explains the sentences in the Qur'an which are still global by referring to the provisions of the Prophet Muhammad SAW. Classification of text documents can also be used to overcome the problem of interrelation between the Qur'an and hadith. The problem of interrelation between books of hadith needs to be done because some hadiths in certain hadith books have the same meaning as other hadith books. This study aims to analyze the development of text representation and classification methods suitable to overcome similarity meaning problems in detecting interrelationships between hadith books. The research method used is Systematic Literature Review (SLR) sourced from Google Scholar, Science Direct, and IEEE. There are 42 pieces of literature that have been studied successfully. The results showed that contextual embedding as the newest text representation method considered word context and sentence meaning better than static embedding. As a classification method, the ensemble method has better performance in classifying text documents than using only a single classifier model. Thus, future research can consider using a combination of contextual embedding and ensemble methods to detect interrelationships between books of hadith.Hadis merupakan sumber rujukan hukum Islam kedua sesudah Al-Qur’an, yang menjelaskan kalimat dalam Al-Qur’an yang masih bersifat global dengan mengacu pada ketetapan Nabi Muhammad SAW. Untuk memudahkan seorang muslim mempelajari Al-Qur’an maupun hadis dapat dilakukan dengan menggunakan klasifikasi dokumen teks. Klasifikasi dokumen teks juga dapat digunakan untuk mengatasi permasalahan interelasi antara Al-Qur’an dan hadis. Namun, sejauh ini belum ada penelitian yang melakukan interelasi antar kitab hadis. Permasalahan interelasi antar kitab hadis perlu dilakukan karena pada beberapa hadis dalam kitab hadis tertentu memiliki kesamaan makna dengan kitab hadis lain sehingga perlu dikelompokkan sesuai dengan topiknya. Tujuan dari penelitian ini adalah menganalisis perkembangan metode representasi teks dan metode klasifikasi supaya dapat ditemukan metode yang cocok untuk mengatasi permasalahan kesamaan makna pada pendeteksian interelasi antar kitab hadis. Metode penelitian yang digunakan adalah Systematic Literature Review (SLR) yang bersumber dari Google Scholar, Science Direct dan IEEE. Setelah melalui proses penilaian kualitas literatur, terdapat 42 literatur yang berhasil dikaji. Hasil penelitian menunjukkan permasalahan kesamaan makna dapat diatasi dengan menggunakan contextual embedding. Contextual embedding merupakan metode representasi teks terbaru, yang mampu mempertimbangkan konteks kata dan makna kalimat lebih baik daripada static embedding. Dalam hal pendeteksian interelasi antar kitab hadis, ditemukan metode yang cocok digunakan sebagai metode klasifikasi adalah metode ensemble. Metode ensemble memiliki kinerja yang lebih baik dalam mengelompokkan dokumen teks, daripada hanya menggunakan single classifier model saja. Dengan demikian, pada penelitian selanjutnya dapat dipertimbangkan penggunaan kombinasi contextual embedding dan metode ensemble untuk deteksi interelasi antar kitab hadis
Sistem Keamanan Helm Berbasis Internet of Things dengan Fitur Pelacakan Menggunakan Android
Get PDFHelmet theft is a problem that is of concern to the public. Information Technology provides may resolve any problems, like Internet of Things-based system that can detect helmet theft and track the location of the helmet if it's stolen. This system is designed using a microcontroller device, namely Arduino which is attached to the helmet and motorbike with the help of the SIM800L v2, GPS Neo-6m, buzzer, and Bluetooth HC-05 which is connected to the master slave as an indicator of the safety of the helmet. The hardware on the helmet is connected to Firebase Realtime Database server so it can be connected with the user's Android application to monitor the state and location of the helmet. Android application displays maps to determine the position of the helmet, and can display notifications when the helmet is being stolen. The conclusion is this system can detect helmet theft with a maximum distance from the master and slave bluetooth connections of 10 meters, and the average data transmission from hardware to Firebase is 1,1 seconds, and can monitor status of the helmet and track the position of the helmet through the Android application with Android Jelly Bean (v4.3) operating system.
Pencurian helm merupakan salah satu masalah yang menjadi perhatian di kalangan masyarakat saat ini. Pemanfaatan Teknologi Informasi memberikan banyak kemudahan untuk mengatasi banyak permasalahan, seperti dengan menggunakan sistem berbasis Internet of Things yang dapat mendeteksi pencurian helm dan melacak lokasi helm jika tercuri. Sistem keamanan helm ini dirancang menggunakan perangkat mikrokontroler yaitu, Arduino yang dipasangkan pada helm dan motor dengan bantuan modul SIM800L v2, GPS Neo-6m, buzzer, dan Bluetooth HC-05 yang dikoneksikan master slave sebagai indikator keamanan pada helm. Perangkat keras pada helm dihubungkan dengan server Firebase Realtime Database sehingga dapat dihubungkan dengan aplikasi Android pengguna untuk memonitor keadaan dan lokasi dari helm. Aplikasi Android menampilkan maps untuk mengetahui posisi helm, dan dapat menampilkan notifikasi apabila helm sedang dalam keadaan tercuri. Kesimpulan dari hasil perancangan sistem keamanan helm yaitu, rancangan sistem pendeteksi helm berbasis IoT dapat mendeteksi pencurian helm dengan jarak maksimal dari koneksi bluetooth master dan slave adalah 10 meter, dan rata-rata pengiriman data dari perangkat keras ke Firebase adalah 1,1 detik, serta dapat melakukan monitoring status helm dan pelacakan posisi helm melalui aplikasi Android dengan sistem operasi Android Jelly Bean(v4.3)
Deteksi Kesamaan Teks Jawaban pada Sistem Test Essay Online dengan Pendekatan Neural Network
Get PDFE-learning is an online learning system that applies information technology in the teaching process. E-learning used to facilitate information delivery, learning materials and online test or assignments. The online test in evaluating students’ abilities can be multiple choice or essay. Online test with essay answers is considered the most appropriate method for assessing the results of complex learning activities. However, there are some challenges in evaluating students essay answers. One of the challenges is how to make sure the answers given by students are not the same as other students answers or 'copy-paste'. This study makes a similarity detection system (Similarity Checking) for students' essay answers that are automatically embedded in the e-learning system to prevent plagiarism between students. In this paper, we use Artificial Neural Network (ANN), Latent Semantic Index (LSI), and Jaccard methods to calculate the percentage of similarity between students’ essays. The essay text is converted into array that represents the frequency of words that have been preprocessed data. In this study, we evaluate the result with mean absolute percentage error (MAPE) approach, where the Jaccard method is the actual value. The experimental results show that the ANN method in detecting text similarity has closer performance to the Jaccard method than the LSI method and this shows that the ANN method has the potential to be developed in further research.E-learning adalah sistem pembelajaran daring yang menerapkan teknologi informasi dalam proses belajar mengajar. Fungsi e-learning adalah untuk mempermudah penyampaian informasi, memberi materi pembelajaran dan mengerjakan soal atau tugas. Penerapan kuis ujian dalam evaluasi kemampuan siswa dapat berupa pilihan ganda atau jawaban essay. Tugas dengan kuis essay dianggap sebagai metode yang paling tepat untuk menilai hasil kegiatan belajar yang kompleks. Namun, ada beberapa tantangan dalam mengevaluasi jawaban essay siswa. Salah satu tantangannya adalah bagaimana memastikan jawaban yang diberikan siswa tidak sama dengan jawaban siswa lain atau ‘copy-paste’ jawaban siswa lain. Penelitian ini membuat sebuah sistem pendeteksi kesamaan (Similarity Checking) untuk jawaban essay siswa secara otomatis tertanam dalam sistem e-learning untuk membantu mencegah plagiarisme antar sesama siswa dalam tugas yang dikerjakan. Dalam paper ini, kami menggunakan metode Artificial Neural Network (ANN), Latent Semantic Index (LSI), dan Jaccard untuk menghitung persentase kesamaan antar essay siswa. Teks essay diubah menjadi array yang mewakili frekuensi kata yang sebelumnya sudah dilakukan preprocessing data. Dalam penelitian ini, kami menggunakan hasil evaluasi dengan pendekatan mean absolute percentage error (MAPE), dimana metode Jaccard sebagai nilai aktualnya. Hasil percobaan menunjukkan bahwa metode ANN dalam pendeteksian kesamaan teks memiliki kinerja yang lebih mendekati metode Jaccard dibandingkan dengan metode LSI dan hal ini menunjukkan kedepannya metode ANN berpotensi untuk dikembangkan pada penelitian lebih lanjut
Perbandingan Naïve Bayes, SVM, dan k-NN untuk Analisis Sentimen Gadget Berbasis Aspek
Get PDFThe Samsung Galaxy Z Flip 3 is one of the gadgets that are currently popular among the public because of its unique shape and features. Youtube is one of the social media that can be accessed and enjoyed by the public, one of which is gadget review content on the GadgetIn channel. Youtube can provide information, whether people accept or are interested in this new gadget or not. This study aims to determine the sentiment of a gadget producer. Based on the results of the analysis and testing that has been carried out on the Youtube comments of the Samsung Galaxy Z Flip 3 gadget with a total of 9,597 comments, more users gave positive opinions in the design aspect and negative opinions on the price, specifications and brand image aspects. By using the CRISP-DM model and comparing the Naïve Bayes (NB), Support Vector Machine (SVM), and k-Nearest Neighbor (k-NN) classification methods, it is proven that the SVM classification model shows the best results. The average accuracy of SVM is 96.43% seen from four aspects, namely the design aspect of 94.40%, the price aspect of 97.44%, the specification aspect of 96.22%, and the brand image aspect of 97.63%.
Samsung Galaxy Z Flip 3 merupakan salah satu gadget yang sedang marak di kalangan masyarakat karena bentuk dan fiturnya yang unik. Youtube merupakan salah satu media sosial yang bisa diakses dan dinikmati oleh masyarakat, salah satunya konten review gadget pada channel GadgetIn. Youtube dapat memberikan informasi, apakah masyarakat menerima atau tertarik pada gadget baru ini atau tidak. Penelitian ini bertujuan untuk mengetahui sentimen dari sebuah produk gadget. Berdasarkan hasil analisis dan pengujian yang telah dilakukan terhadap komentar Youtube gadget Samsung Galaxy Z Flip 3 dengan total 9,597 komentar, lebih banyak pengguna yang memberikan opini positif dalam aspek desain dan opini negatif pada aspek harga, spesifikasi dan citra merk. Dengan model CRISP-DM dan membandingkan metode klasifikasi Naïve Bayes (NB), Support Vector Machine (SVM), dan k-Nearest Neighbor (k-NN), terbukti bahwa model klasifikasi SVM menunjukkan hasil terbaik. Rata-rata accuracy SVM sebesar 96.43% dilihat dari empat aspek, yaitu aspek desain sebesar 94.40%, aspek harga sebesar 97.44%, aspek spesifikasi sebesar 96.22%, dan aspek citra merk sebesar 97.63%
Sistem Keamanan Gedung Menggunakan Kinect Xbox 360 Dengan Metode Skeletal Tracking
Get PDFThe incidence of fire and theft is very threatening and causes disruption to people's lifestyles, both due to natural and human factors resulting in loss of life, damage to the environment, loss of property and property, and psychological impacts. The purpose of this study is to create a building security system using Kinect Xbox 360 which can be used to detect fires and loss of valuable objects. The data transmission method uses the Internet of Things (IoT) and skeletal tracking. Skeletal detection uses Arduino Uno which is connected to a fire sensor and Kinect to detect suspicious movements connected to a PC. Kinect uses biometric authentication to automatically enter user data by recognizing objects and detecting skeletons including height, facial features and shoulder length. The ADC (Analog to Digital Converter) value of the fire sensor reading has a range between 200-300. The fire sensor detects the presence of fire through optical data analysis containing ultraviolet, infrared or visual images of fire. The data generated by Kinect by detecting the recognition of the skeleton of the main point of the human body known as the skeleton, where the reading point is authenticated by Kinect from a range of 1.5-3 meters which is declared the optimal measurement, and if a fire occurs, the pump motor will spray water randomly. to extinguish the fire that is connected to the internet via the wifi module. The data displayed is in the form of a graph on the Thingspeak cloud server service. Notification of fire and theft information using the delivery system from input to databaseKejadian kebakaran dan kemalingan sangat mengancam serta menyebabkan gangguan pada pola hidup masyarakat, baik karena faktor alam maupun manusia sehingga timbul korban jiwa, lingkungan rusak, rugi dalam hal harta dan benda, serta berdampak pada psikologis. Tujuan dari penelitian ini membuat sistem keamanan gedung menggunakan kinect xbox 360 yang dapat dipergunakan untuk mendeteksi kebakaran serta kehilangan benda berharga. Metode pengiriman data menggunakan Internet of Things (IoT) dan skeletal tracking deteksi skeleton dengan memakai arduino uno yang terhubung ke sensor api serta kinect untuk mendeteksi pergerakan yang mencurigakan yang terhubung ke PC. Kinect menggunakan otentikasi biometric untuk memasukan data pengguna secara otomatis dengan mengenali object dan mendeteksi skeleton diantaranya tinggi badan, fitur wajah dan Panjang bahu. Nilai ADC (Analog to Digital Converter) pembacaan sensor api memiliki range antara 200-300. Sensor api mendeteksi adanya api melalui analisis data optic yang mengandung pancaran ultraviolet, infrared atau pencitraan visual api. Data yang dihasilkan kinect dengan mendeteksi pengenalan kerangka titik utama tubuh manusia yang di kenal sebagai skeleton, dimana titik pembacaan yang terotentikasi oleh Kinect dari rentang 1, 5-3 meter yang dinyatakan pengukuran optimal, dan apabila terjadinya kebakaran maka motor pompa akan menyemburkan air secara acak untuk memadamkan api yang dikoneksikan dengan internet melalui modul wifi. Data yang ditampilkan berbentuk grafik pada layanan cloud server thingspeak. Pemberitahuan informasi kebakaran dan kemalingan menggunakan sistem pengiriman dari input ke database
High Scalability Document Clustering Algorithm Based On Top-K Weighted Closed Frequent Itemsets
Get PDFDocuments clustering based on frequent itemsets can be regarded a new method of documents clustering which is aimed to overcome curse of dimensionality of items produced by documents being clustered. The Maximum Capturing (MC) technique is an algorithm of documents clustering based on frequent itemsets that is capable of producing a better clustering quality in compared to other similar algorithms. However, since the maximum capturing technique employed frequent itemsets, it still suffers from such several weaknesses as the emergence of items redundancy that may still cause curse of dimensionality, difficult to determine the minimum support value from a set of documents to be clustered, and no weighting on items incurred to the resulting frequent itemsets. To cope with those various weaknesses, in this research, an algorithm of documents clustering based on weighted top-k closed frequent itemsets, which is called as Weighted Maximum Capturing (WMC) algorithm, is developed. The proposed algorithm involves the frequent pattern tree algorithm to mine closed frequent itemsets from a set of documents without specifying the minimum support value of items to be generated. Experimental results showed that improvement on the resulting clustering accuracy was produced. The resulting average values of F-measure of 0.713 and purity of 0.721 with improvement ratio of 1.4% for F-measure and 2% for purity. Nevertheless, results of the scalability test showed very significant improvement. The WMC algorithm only requires the average computing time of 623.77 minutes, 518.05 minutes faster than the average computing time required by the MC algorithm.Documents clustering based on frequent itemsets can be regarded a new method of documents clustering which is aimed to overcome curse of dimensionality of items produced by documents being clustered. The Maximum Capturing (MC) technique is an algorithm of documents clustering based on frequent itemsets that is capable of producing a better clustering quality in compared to other similar algorithms. However, since the maximum capturing technique employed frequent itemsets, it still suffers from such several weaknesses as the emergence of items redundancy that may still cause curse of dimensionality, difficult to determine the minimum support value from a set of documents to be clustered, and no weighting on items incurred to the resulting frequent itemsets. To cope with those various weaknesses, in this research, an algorithm of documents clustering based on weighted top-k closed frequent itemsets, which is called as Weighted Maximum Capturing (WMC) algorithm, is developed. The proposed algorithm involves the frequent pattern tree algorithm to mine closed frequent itemsets from a set of documents without specifying the minimum support value of items to be generated. Experimental results showed that improvement on the resulting clustering accuracy was produced. The resulting average values of F-measure of 0.713 and purity of 0.721 with improvement ratio of 1.4% for F-measure and 2% for purity. Nevertheless, results of the scalability test showed very significant improvement. The WMC algorithm only requires the average computing time of 623.77 minutes, 518.05 minutes faster than the average computing time required by the MC algorithm
Rancang Bangun Perangkat Komunikasi Adaptif Untuk Pengembangan QoS (Quality of Service) Infrastruktur Internet of Vehicle (IoV)
Get PDFThe communication network is an important and vital component in the implementation of the Internet of Vehicle (IoV). The characteristics of IoV related to mobility, load, coverage area is very complex. The movement of connected nodes, communication load and wide coverage require reliable infrastructure support. Coupled with a high level of Quality of Service (QoS) for Internet of Vehicle (IoV) implementation which has a high risk if a communication system failure occurs. In this research, a system that has adaptive capability has been built in choosing a good connection infrastructure at the point where the unit is connected. Created a system that has the ability to connect to several communication network infrastructure. The system can switch to another provider when there is a connection that decreases its QoS level. The tests carried out resulted in better connection dynamics because there was an infrastructure backup. Although there are still many weaknesses because the distribution of network availability is still problematic. Anticipation of network overload can be anticipated with this system. The test results show that there is an increase in the percentage of lines connected to the new system. There is an increase in the percentage of connectivity around 10% to 20% compared to systems without connection backups.
Jaringan komunikasi adalah komponen yang sangat penting dan vital dalam implementasi Internet of Vehicle (IoV). Karakteristik dari IoV terkait dengan mobilitas, beban, coverage area sangatlah kompleks. Pergerakan node terhubung, beban komunikasi dan lingkup area yang luas membutuhkan dukungan infratsruktur yang handal. Ditambah lagi dengan level QoS yang tinggi untuk impelementasi IoV yang memiliki resiko tinggi jika muncul kegagalan sistem komunikasi. Dalam penelitian ini dibangun sebuah sistem yang memiliki kemampuan adaptif dalam memilih infrastruktur koneksi yang bagus di titik lokasi unit/node terhubung. Dibuat sebuah sistem yang memiliki kemampuan koneksi ke beberapa infrastruktur jaringan komunikasi. Sistem tersebut dapat berpindah ke provider lain ketika terjadi koneksi yang menurun level QoS-nya. Pengujian yang dilakukan menghasilkan dinamika koneksi yang lebih baik karena terdapat backup infrastruktur. Meskipun masih banyak kelemahan karena sebaran kesediaan jaringan masih bermasalah. Sebaran jaringan menggunakan teknologi seluler (3G/4G) hampir sama antar provider sehingga sistem tidak berhasil menangani masalah blank spot. Perlu dikembangkan menggunakan teknologi komunikasi lain seperti LoRa. Antisipasi terhadap overload jaringan dapat diantisipasi dengan sistem ini. Hasil pengujian menunjukkan terdapat peningkatan prosentase jalur yang terkoneksi dengan sistem baru. Terdapat peningkatan prosentase konektifitas sekitar 10% sd 20% dibandingkan dengan sistem tanpa backup koneksi
Pengembangan Aplikasi Asisten Pintar Pembuka Al Qur’an 30 Juz dengan Perintah Voice Command
No full textMany developers of digital Qur'an applications today still use tap to scrolling to run applications, although the features are interesting. This makes it less effective and efficient in opening the Qur'an. As is the case during the taklim assembly, some da'i are very interactive with jama'ah, asking to open certain surahs and verses so that there are some who have difficulty in searching. Therefore, the need for the Qur'anic application with voice command command to facilitate users. This research is the development of the Qur'an application with voice recognition feature. Using the waterfall method in development, voice command with google speech API as a voice command of surah and verse calling in the Qur'an application 30 juz. Conducted 10 randomized experiments with calls in the form of play or open surahs and certain verses give a 90% accuracy result. Commands can be given when online or offline. Then the use of google speech API can be very useful for use in the development of other applications.
Banyak developer aplikasi Al-Qur’an digital saat ini masih menggunakan tap hingga scrolling untuk menjalankan aplikasi, meskipun fiturnya menarik. Hal itu menjadikan kurang efektif dan efisien dalam membuka Al-Qur’an. Seperti halnya saat majelis taklim, beberapa da’i sangat interaktif dengan jama’ah, meminta untuk membuka surah dan ayat tertentu sehingga ada beberapa yang kesulitan dalam mencari. Oleh karena itu perlunya aplikasi Al Qur’an dengan perintah voice command untuk memudahkan pengguna. Penelitian ini merupakan pengembangan aplikasi Al Qur’an dengan fitur voice recognition. Menggunakan metode waterfall dalam pengembangan, voice command dengan google speech API sebagai perintah suara pemanggilan surah dan ayat dalam aplikasi Al Qur’an 30 juz. Dilakukan 10 kali percobaan secara acak dengan pemanggilan berupa putar atau buka surah dan ayat tertentu memberikan hasil akurasi 90%. Perintah bisa diberikan ketika dalam keadaan online maupun offline. Maka penggunaan google speech API dapat sangat berguna untuk digunakan dalam pengembangan aplikasi lainnya