Cities worldwide have been trying to achieve a sustainable urban form to handle their rapid urban growth. Many sustainable urban forms have been studied and two of them, the compact city and the eco city, were chosen in this study as urban form foundations. Based on these forms, four sustainable city criteria (compactness, compatibility, dependency, and suitability) were considered as necessary functions for land use optimisation. This study presents a land use optimisation as a method for achieving a sustainable urban form. Three optimisation methods (particle swarm optimisation, genetic algorithms, and a local search method) were combined into a single hybrid optimisation method for land use in Bekasi city, Indonesia. It was also used for examining Bekasi city’s land-use-plan (2010–2030) after optimising current (2015) and future land use (2030). After current land use optimisation, the score of sustainable city criteria increased significantly. Three important centres of land use (commercial, industrial, and residential) were also created through clustering the results. These centres were slightly different from centres of the city plan zones. Additional land uses in 2030 were predicted using a nonlinear autoregressive neural network with external input. Three scenarios were used for allocating these additional land uses including sustainable development, government policy, and business-as-usual. Future land use allocation in 2030 found that the sustainable development scenario showed better performance compared to government policy and business-as-usual scenarios.

To overcome the COVID-19 outbreak, the government did not carry out the lockdown policy (regional quarantine policy) but implemented the Large-Scale Social Restrictions (PSBB) policy. Starting from the capital city of Jakarta, this policy was followed by other regions. Bekasi City as a buffer zone of Jakarta immediately implemented the PSBB policy since this area is close to Jakarta and is feared to be affected by the Jakarta region which is a red zone with almost half of Indonesian COVID-19 cases are in the Jakarta area. Many people do not agree with the PSBB, but in order to keep the economic growth as well as to overcome the outbreak, the government does not adopt a regional quarantine policy. To determine the effectiveness of PSBB in the city of Bekasi, this study tried to use the Susceptible-Infected-Recovered (SIR) model to measure the spread rate of COVID-19. The results showed a decrease in the number of infected cases with beta and gamma were 0.071 and 0.05, respectively, and the epidemic was predicted to end in June 2020. Keywords: coronavirus, epidemic, pandemic, regional quarantine policy, Bekasi City Abstrak Dalam mengatasi wabah COVID-19, pemerintah tidak melakukan karantina wilayah (lock down) tetap menggunakan kebijakan Pembatasan Sosial Berskala Besar (PSBB). Dimulai dari ibukota Jakarta, kebijakan ini diikuti oleh wilayah lainnya. Kota Bekasi sebagai wilayah penyangga Jakarta segera menerapkan kebijakan PSBB mengingat wilayah ini berdekatan dengan Jakarta dan dikhawatirkan terpengaruh dengan kota Jakarta yang merupakan zona merah dengan hamper separuh kasus COVID-19 ada di wilayah Jakarta. Banyak pihak yang mendukung dan juga kurang setuju dengan PSBB, namun agar perekonomian tetap berjalan dan wabah dapat diatasi, pemerintah tidak mengambil kebijakan karantina wilayah. Untuk mengetahui efektifitas PSBB di kota Bekasi, penelitian ini mencoba menggunakan model Susceptible-Infected-Recoverd (SIR) untuk mengukur laju penyebaran COVID-19. Hasilnya menunjukan adanya laju penurunan kasus terinfeksi dengan beta dan gamma beruturut-turut sebesar 0,071 dan 0,05 dan diprediksi akan berakhir di bulan Juni 2020. Kata kunci: virus corona, epidemik, pandemik, karantina wilayah, Bekasi City

Tourism is the sources of income which is influenced by customer satisfaction. One way to know customer satisfaction is feedback, one of which is a review using an application. One of the feedback applications is Google Review. Such applications are have been widely used, for example in this study in this case study, Summarecon Mal Bekasi, can reach 60,000 comments. To find out the sentiment of the large number of comments, it is necessary to use computational tools. The current research applies sentiment analysis using the Naïve Bayes method and the Support Vector Machine. Data retrieval is done by web scrapping technique. Furthermore, the comment data is processed by pre-processing and labelling using the Lexicon dictionary. The process of applying sentiment analysis is carried out to determine whether the comments are positive or negative. In this study, the accuracy of the Naïve Bayes and Support Vector Machine methods in conducting sentiment analysis on the Summarecon Mal Bekasi review with a data of 2,143 comments with an accuracy for Naïve Bayes and Support Vector Machine 80.95% and 100% respectively. A Jason-style application is built to show the implementation in Flask framework. Keywords:

Penggunaan internet untuk aktivitas transaksi bisnis dikenal dengan istilah Electronic Commerce (E-commerce). Hal ini ditandai dengan meningkatnya jumlah pengusaha yang menggunakan e-commerce dalam perusahaannya. Digital marketing memudahkan pebisnis memantau dan menyediakan segala kebutuhan dan keinginan calon konsumen, di sisi lain calon konsumen juga bisa mencari dan mendapatkan informasi produk hanya dengan cara menjelajah dunia maya sehingga mempermudah proses pencariannya. Mitra dari kegiatan pengabdian kepada masyarakat yaitu guru SMA Negeri 14 Bekasi. Hal ini dilakukan sebagai upaya pengenalan dalam pengoptimalan penggunaan smartphone yang tidak hanya digunakan untuk sekedar menulis pesan, melakukan panggilan dan bersosial media saja, namun dapat juga dijadikan sebagai media yang mampu mendukung kegiatan usaha atau bisnis yang dimiliki oleh beberapa Guru. Pelaksanaannya materi yang dipaparkan mengenai pengantar digital marketing dan teknis penggunaan salah satu ­e-commerce Shopee. Metode pelaksanaan kegiatan ini dimulai dari penyuluhan, pelatihan dan evaluasi. Hasil dari kegiatan pelatihan menunjukkan para peserta antusias dengan adanya kegiatan ini dan menganggap materi yang dipaparkan sangat menarik dan bermanfaat.

For the first time, machine learning did the classical classification process using two classes (bi-class) such as class -1 and class +1, 0 and 1, or the form of categories such as true and false. Famous methods used are Artificial Neural Networks (ANN) and Support Vector Machine (SVM). The current development was a problem with more than two classes, known as multi-class classes. For SVM sometimes the plural classes are overcome by doing a gradual process like a decision tree (DT) method. Meanwhile, ANN has experienced rapid development and is currently being developed with a large number of layers with the new activation functions, i.e. the rectified linear units (ReLu), and the probabilistic-based activation, i.e. softmax, including its optimizer methods (adam, sgd, and others). Then the term changed to Deep Learning (DL). This study aimed to compare two well-known methods (DL and SVM) in classifying multiple classes. The number of DL layers was six with the neuron composition are 128, 64, 32, 8, 4, and 3, while SVM uses a radial kernel base function with gamma and c respectively 0.7 and 5. Besides, this study intends to compare the use of the Graphics Processing Unit (GPU) available on Google Interactive Notebook (Google Colab), an online Python language programming application. The results showed that DL accuracy outperformed SVM but required large computational resources, with the accuracy for DL and SVM are 99% and 98%, respectively. However, the use of the GPU can overcome these problems and is proven to increase the speed of the process as much as 47 times. Keywords: Artificial Neural Networks, Graphics Processing Unit, Google Interactive Notebook, Rectified Linear units, Support Vector Machine. Abstrak Di awal perkembangannya mesin pembelajaran melakukan proses klasikfikasi menggunakan dua kelas (bi-class) misalnya kelas -1 dan kelas +1, 0 dan 1, atau bentuk kategori seperti benar dan salah. Metode terkenal yang digunakan adalah Jaringan Syaraf Tiruan (JST) dan Support Vector Machine (SVM). Perkembangan selanjutnya adalah problem dengan kelas yang lebih dari dua kelas, dikenal dengan istilah kelas jamak (multi-class). Untuk SVM terkadang kelas jamak diatasi dengan melakukan proses berjenjang mirip pohon keputusan (decision tree). Sementara itu JST telah mengalami perkembangan yang pesat dan saat ini sudah dikembangkan dengan jumlah layer yang banyak disertai dengan fungsi-fungsi aktivasi terkini seperti rectified linear unit (ReLu), dan softmax yang berbasis probabilistik, termasuk juga metode-metode optimizernya (adam, sgd, dan lain-lain). Kemudian istilahnya berubah menjadi Deep Learning (DL). Penelitian ini mencoba membandingkan dua metode terkenal (DL dan SVM) dalam melakukan klasifikasi kelas jamak. Jumlah layer DL sebanyak enam dengan masing-masing neuron sebesar 128, 64, 32, 8, 4, dan 3, sementara SVM menggunakan kernel radial basis function dengan gamma dan c berturut-turut 0.7 dan 5. Selain itu penelitian ini bermaksud membandingkan penggunaan Graphics Processing Unit (GPU) yang tersedia di Google Interactive Notebook (Google Colab), sebuah aplikasi online pemrograman bahasa Python. Hasil penelitian menunjukan akurasi DL unggul tipis dibanding SVM namun memerlukan sumber daya komputasi yang besar masing-masing dengan akurasi 99% dan 98%. Namun penggunaan GPU mampu mengatasi permasalahan tersebut dan terbukti meningkatkan kecepatan proses sebanyak 47 kali. Kata kunci: Jaringan Syaraf Tiruan, Graphics Processing Unit, Google Interactive Notebook, Rectified Linear units, Support Vector Machine.

Urban areas have been perceived as the source of environmental problems. To avoid improper land use allocation, negative sprawl effects, and other sources of environmental degradation, city planners need tools for simulating and optimizing their proposed plans. This study proposed a “what-if” analysis model that could help the planners in assessing and simulating their urban plans in Bekasi City, Indonesia. As part of Jakarta Metropolitan Area which exhibited a “post-suburbanization” phenomenon, this city faces many problems because of its high urban growth. Since the urban area has higher land use density than the rural area, especially on built-up class, it needs more consideration when allocating this kind of land use. Because each type of built-up class influences another type, it is difficult to allocate manually. Therefore, this study proposed a land-use optimization application to help planners finding the appropriate land use. This study showed that a model with simulation and optimization can be used to handle urban growth.