Telkom Institute of Management

tujuan penelitian ini adalah untuk mengetahui apakah ada pengaruh citra merek dan harga terhadap keputusan pembelian pada STIM Sukma Medan. Sampel penelitian 144 orang mahasiswa tahun 2013 sampai tahun 2015, pengambilan sampel menggunakan random sampling Analisis data menggunakan uji Regresi Berganda, pengujian hipotesis menggunakan uji koefisien determinasi (R2), uji parsial (uji t), dan uji simultan (uji F), sedangkan pengolahan data menggunakan SPSS 20. Hasil penelitian menunjukkan bahwa dari uji koefisien determinasi (R2) variabel citra merek dan harga mampu menjelaskan keberadaannya terhadap variabel keputusan pembelian, selain itu secara parsial citra merek tidak berpengaruh dan tidak signifikan terhadap keputusan pembelian sementara harga berpengaruh positif dan signifikan terhadap keputusan pembelian, secara simultan citra merek dan harga berpengaruh positif dan signifikan terhadap keputusan pembelian

Indonesia is a tropical country that experiences forest fires every year. Forest fires occur due to a prolonged summer season. A major effect of forest fires that commonly occurred in Indonesia is the respiratory disorder and the visual impairment caused by the thick smoke that can experienced by the people who lives around the forest. The effects of forest fire fumes when the forest fire spread across the bigger land or area are also experienced by neighboring countries such as Malaysia, Singapore and Brunei Darussalam. Forest is a habitat for many animals, one of which is a bird. Birds are able to communicate with their colonies through sound. The bird sound during communication to the group can be in the form of calls, marriage invitations, and warnings of danger or threat of forest fires. This paper presents bird sounds classification study using one of Deep Learning (DL) algorithms i.e. Convolutional Neural Network (CNN) method. The CNN method is used to classify bird sounds in the two conditions: (1) under normal circumstances or conditions, and (2) under threated or panic condition. The bird sound data used in this study were collected from the local birds in Indonesia. The classification result of two bird sounds based on CNN method achieved up to 96.45%. This paper is a preliminary study for bio inspired early warning of forest fires based on the sound of birds.

The lower Davies Bouldin Index (DBI) is considered the best clustering algorithm based on the criteria that yields a cluster set. The purpose of this research is to optimize the clustering results using DBI. The data sources used are the number of villages that have school facilities and the level of education is obtained from the government website (https://www.bps.go.id). The level of education in question is senior high school and vocational high school. The method used is k-means. The results show that from the number of clusters (k = 2, 3, 4, 5, 6) the optimal DBI for (k = 2) is obtained with a value of 0.168 for Measure Type = Mixed Measures. For the value of k = 2, a mapping of areas with L0 (low) = 31 province and L1 (high) = 3 provinces is obtained. The final centroids obtained for each cluster are L0 (315 and 155) and L1 (1710 and 1259). Based on the results of mapping by optimizing k-means and DBI, more than 90% of the villages still have school facilities, especially at the high school and vocational high school levels.

Medical images have been used as one of the objects to diagnose the patient. A digitally formatted medical image is easier to be stored and distributed but also easier to be modified for illegal purposes. Digital image watermarking offers a solution to protect digital medical images. By embedding fragile authentication watermark, the watermarking system can detect and localize the tampered area of medical images. Moreover, by embedding the feature extraction in the form of average intensities of the image, an original image can be recovered from the tampered image. This paper will study and test a watermarking scheme using LSB Modification to perform tamper detection and recovery in the ROI. To make this watermarking scheme reversible, RLE is used to embed the original LSBs in the RONI to get higher embedding capacity. The experimental results show that this watermarking system can detect and localize tamper with up to 100% accuracy and perform image recovery up to 100% recovery rate until 20% of tempered area in ROI.

penelitian ini bertujuan untuk mengetahui pengaruh motivasi dan kompensasi terhadap kinerja karyawan. Penelitian ini dilakukan pada 65 orang karyawan PT. Kereta Api Indonesia cabang Rantau Prapat dengan sampling jenuh. Variabel yang diamati dalam penelitian ini terdiri dari motivasi dan kompensasi sebagai variabel independen. Data dikumpulkan dengan penyebaran kuisioner dan studi pustaka, kuisioner dikembangkan dari indikator  masing-masing variabel yang menjadi pengamatan. Uji data dilakukan dengan validitas dan reliabilitas. Analisis data menggunakan regresi linier berganda dengan uji hipotesis koefisien determinasi, uji simultan dan uji parsial. Hasil penelitian ini menunjukkan bahwa kompensasi berpengaruh positif dan signifikan terhadap kinerja karyawan, motivasi tidak berpengaruh terhadap kinerja karyawan.

Imbalanced data classification is challenging task for various datasets in the real world. One of technique to enlarge the sample in minority class is oversampling to fix size as majority class. This research aims to test SMOTE, Borderline-SMOTE, and ADASYN to handle dataset imbalance and to observe its impact toward classification accuracy. Gradient Boosting applied as a classifier and seven datasets are used in this research. Accuracy, recall, precision, F1-Score, AUC were also implemented to measure classifier performance. Experiments showed that oversampling technic increase accuracy from 2% to 11% for the dataset Mammography, Liver Disorders, Diabetes (Pima Indian), Indian Liver, Habberman, and Immunotherapy. Borderline-SMOTE increases higher accuracy compared to other oversampling method. Surprisingly, Breast Cancer Wisconsin has steady accuracy with or without oversampling. Even though, oversampling good for data imbalanced, the sensibility of oversampling algorithm and the nature of dataset must considered.

The inequality of digital skills is an organizational challenge experienced by public and private organizations to ensure work productivity in work-from-home arrangements during Covid-19. This article aims to elaborate on digital skill development and examine the effects of digital leadership and digital collaboration on digital skill development. This article is based on a cross-sectional study involved 824 office workers from 32 provinces in Indonesia. The combined convenience and snowballing approach were used as the sampling methods. The collected data were structured in the first-order constructs by PLS Structural Equation Modeling. The results revealed that digital skills are significantly influenced directly by digital collaboration and indirectly by digital leadership. For accelerating digital skill development, the superior of office workers should facilitate their team members to collaborate intensively by using digital technology. Further study is recommended to examine the effects of other factors such as work motivation, family support, and availability of digital facility at home, performance management, and perceived organizational support.

Abstract Nowadays, Teaching and learning activities in the world of education must always follow the development of technology. The use of these technologies will make these activities more effective and efficient. Gamification is part of innovation in education. In this research, gamification is used as a tool for studying activities in project management information systems subject. The method used is technology-based applied research. The Assessment Tool in this study uses Quizizz. Quizizz is used on midterms. This exam was attended by 29 students of the information systems department STMIK Royal. The questionnaire was made using a Mentimeter. The use of Quizizz has a positive impact. The level of student answers questions correctly is 51%. Then 66% prefer Quizizz as assessment tool compared to paper and google forms.

Diagram UML merupakan sebuah alat bantu bagi seorang pengembang aplikasi untuk mendesain sistem. Penelitian yang dilakukan adalah perancangan perangkat lunak menggambar diagram UML berbasis android untuk meningkatkan mobilitas seorang pengembang aplikasi. Tujuan dari penelitian ini adalah untuk mengetahui informasi ketentuan setiap diagram UML khususnya use case diagram, activity diagram, dan class diagram untuk kebutuhan seorang analis dalam membangun sebuah sistem informasi. Membantu pengguna untuk menggambar diagram secara mobile, membantu pembelajaran analisis dan desain perancangan sebuah sistem informasi, dan sebagai penerapan dan pengembangan dari ilmu grafika komputer dan sistem informasi yang sudah dipelajari dan ditempuh selama perkuliahan. Metode penelitian yang digunakan adalah dengan menggunakan model System Development Life Cycle (SDLC) Prototype. Hasil penelitian yang didapatkan menunjukkan bahwa analisis, perancangan dan pengujian aplikasi menggambar diagram “Vistchart” pada aplikasi ini, pengguna memilih menu diagram yang akan digambar yaitu use case diagram, activity diagram atau class diagram.

Penyebaran berita saat ini semakin tersebar??? luas semenjak perkembangan dunia internet yang semakin pesat. Perkembangan dunia internet membuat berita yang??? tersebar semakin beragam dan berjumlah??? sangat besar. Pembaca berita akan kesulitan untuk memperoleh berita yang diinginkan??? jika berita tersebut tidak terkelompok dengan baik. Dan jika harus dikelompokkan secara manual membutuhkan waktu yang sangat lama. Oleh sebab itu, Clustering menjadi solusi untuk mengatasi masalah tersebut. Clustering akan??? mengelompokkan dokumen berita berdasarkan??? tingkat kemiripan dari dokumen tersebut. Metode Single Linkage merupakan metode pengelompokan hierarchical clustering. Metode Single Linkage mengelompokkan dokumen didasarkan pada jarak terdekat antar dokumen. Komputasi Single Linkage merupakan komputasi yang mahal dan kompleks.??? Sedangkan metode K-means merupakan metode pengelompokan partitioned clustering. Metode K-means mengelompokkan dokumen didasarkan pada jarak terdekat dengan centroid-nya. K-Means merupakan??? metode pengelompokan yang sederhana dan dapat digunakan dengan mudah. Tetapi pada jenis data tertentu, K-means tidak dapat memberikan segementasi data dengan baik, sehingga kelompok yang terbentuk tidak murni data yang sama. Metode pengujian yang digunakan untuk mengukur kualitas cluster adalah Silhouette Coefficient dan Purity. Berdasarkan hasil pengujian yang dilakukan, dapat disimpulkan, bahwa metode Single Linkage memiliki performansi yang lebih baik dibandingkan dengan metode K-means. Nilai silhouette coefficient Single Linkage selalu lebih unggul dibandingkan dengan??? K-Means. Pertambahan jumlah dokumen membuat nilai silhouette coefficient single linkage semakin kecil sedangkan K-means terkadang menghasilkan nilai yang negatif. Untuk nilai purity, Single Linkage selalu bernilai 1 sedangkan K-Means tidak pernah bernilai 1. Hasil pertambahan jumlah cluster dan jumlah dokumen memberikan pengaruh terhadap nilai silhouette coefficient dan purity. Hal ini berarti single linkage selalu menghasilkan dokumen yang sama, sedangkan K-means masih bercampur dengan dokumen yang lain.

Tujuan penelitian ini adalah untuk mengetahui analisis faktor-faktor yang mempengaruhi pendapatan asli daerah (pad) kota tebing tinggi. Penelitian ini bertujuan untuk menganalisa dan mengetahui pengaruh pajak, retribusi dan pendapatan asli lain yang sah terhadap PAD di Kota Tebing Tinggi tahun 2001-2012. Metode analisis yang digunakan dalam penelitian ini adalah menggunakan analisis regresi dengan metode Simultan. Pengujian menggunakan Uji statistik meliputi uji t, uji F dan R-square (koefisien determinasi) serta uji asumsi klasik. dimana semua pengujian tersebut menggunakan alat bantu program Eviews 6.0 dengan data time series tahunan Periode 2001-2012 yang bersumber dari Badan Pusat Statistik. Pada model PAD menunjukkan bahwa konsumsi (CONS) berpengaruh positif dan signifikan pada α = 10 persen, variabel Produk Domestik Regional Bruto (PDRB) berpengaruh positif dan signifikan pada α = 10 persen, dan variabel jumlah penduduk (POP) berpengaruh  positif dan signifikan pada α = 10 persen dan variabel Retribusi tahun sebelumnya berpengaruh negatif dan tidak signifikan terhadap Pandapatan Asli Daerah (PAD) di Kota Tebing Tinggi. Model TAX menunjukkan bahwa variabel konsumsi (CONS) berpengaruh positif dan signifikan pada α = 10 persen dan variabel pajak daerah tahun sebelumnya (TAX1) berpengaruh positif tapi tidak signifikan pada α = 10 persen. Model RET menunjukkan bahwa variabel Produk Domestik Regional Bruto (PDRB) berpengaruh negatif dan dan tidak signifikan pada α = 10 persen, variabel jumlah penduduk (POP) tidak berpengaruh signifikan pada α = 10 persen dan variabel retribusi daerah tahun sebelumnya (RET1) berpengaruh positif dan tidak signifikan pada α = 10 persen. Sedangkan pada model OTHS menunjukkan bahwa variabel jumlah penduduk tidak berpengaruh signifikan pada α = 10 persen, variabel pendapatan asli daerah (PAD) berpengaruh positif dan signifikan pada α = 10 persen

The occurrence of imbalanced class in a dataset causes the classification results to tend to the class with the largest amount of data (majority class). A sampling method is needed to balance the minority class (positive class) so that the class distribution becomes balanced and leading to better classification results. This study was conducted to overcome imbalanced class problems on the Indian Pima diabetes illness dataset using k-means-SMOTE. The dataset has 268 instances of the positive class (minority class) and 500 instances of the negative class (majority class). The classification was done by comparing C4.5, SVM, and naïve Bayes while implementing k-means-SMOTE in data sampling. Using k-means-SMOTE, the SVM classification method has the highest accuracy and sensitivity of 82 % and 77 % respectively, while the naive Bayes method produces the highest specificity of 89 %.

Purpose The purpose of this paper is twofold: first, to investigate the relationship between office redesign and employee productivity; and second to highlight the impact of privacy on work productivity across different generations. Design/methodology/approach This study examines open-office policy more comprehensively by integrating socio-behavioral and physical aspects of the office, and by using a mixed-method approach that incorporates most significant change, factor analysis and hierarchical regression analysis. Using a census method, the respondents were all consultants and trainers in an educational institution who were experiencing office design changes from a combi, cellular-like office to a more open, non-territorial office. Findings Three variables emerged as impacts of office redesign perceived by respondents: friendship, collaboration and privacy. Collaboration and privacy exert a positive influence on work productivity, while friendship does not. The relationship between privacy and work productivity is stronger for the Generation Y than for senior employees, namely, the Baby Boomers and Generation X. Research limitations/implications This study examines the impacts of office redesign in one organization. Future studies should advance the findings by empirically testing the theoretical model in broader contexts. Future studies could also enrich the literature by bringing cultural aspects into the discussion and comparing Asian-based and European or Western-based findings. Practical implications For Gen Y employees who prefer freedom, mobility and flexibility to personalization in their workplace, the open office could be a better solution for organizations that aim for both work productivity and efficiency. Originality/value This study provides an empirical value by using a mixed method of qualitative and quantitative research. This study further contrasts the different perspectives of an office redesign between younger and older generations.

Purpose The purpose of this study is to examine the relationship between supply chain collaboration and innovation. It particularly investigates the effect of collaboration on radical innovation and highlights the positive impact of innovation, both radical and incremental, on business performance. Design/methodology/approach A survey of 230 Indonesian firms was conducted and the instrument was tested for reliability and validity to warrant its psychometric properties. The data were analyzed using structural equation modeling. Findings This study reveals that collaboration with suppliers brings radical innovation, while collaboration with customers brings incremental innovation. Contrary to this study’s conjecture, albeit interesting, collaboration with customers negatively affects radical innovation. Both radical and incremental innovations further exert a positive influence over firm performance. Research limitations/implications This study focuses on the relationships between supply chain collaboration, innovation and firm performance. The results enhance our understanding of types of innovation that are promoted by each dimension of collaboration. Further studies could extend the research by using a more elaborate measure of innovation or perform a longitudinal examination. Practical implications Managers are encouraged to pursue innovation as it improves firm performance. They could exploit their current partnership with customers to generate incremental innovation or leverage their supplier network to develop radical innovation. Originality/value Studies that specifically investigate the impact of firms’ collaboration with their supply chain partners on radical innovation are quite scarce. This empirical study is among the very few to fill this void by providing an integrative assessment of customer, supplier and internal collaborations and their impact on both radical and incremental innovation.

Speech to text was one of speech recognition applications which speech signal was processed, recognized and converted into a textual representation. Hidden Markov model (HMM) was the widely used method in speech recognition . However, the level of accuracy using HMM was strongly influenced by the optimalization of extraction process and modellling methods . Hence in this research, the use of genetic algorithm (GA) method to optimize the Ergodic HMM was tested. In Hybrid HMM-GA, GA was used to optimize the Baum-Welch method in the training process. It was useful to improve the accuracy of the recognition result which is produced by the HMM parameters that generate the low accuracy when the HMM are tested. Based on the research, the percentage increases the level of accuracy of 20% to 41%. Proved that the combination of GA in HMM method can gives more optimal results when compared with the HMM system that not combine with any method.

Air has an important function and role in the lives of humans and other living beings. Every living things needs clean air to support its life optimally, its quality needs to be maintained. A good and healthy level of air quality is one of the main factors in creating a healthy and comfortable environment if the air quality is bad then there will be pollution that will interfere with the health of every population that inhaled. In this research, the author utilizes the Internet of Things (IoT) technology to monitor the condition of air quality levels such as temperature, air humidity, CO and CO2. The system uses ATmega328P-AU as a controller, DHT22 sensor for temperature and air humidity, MQ-7 sensor for CO gas, MQ-135 sensor for CO2 gas, LPWAN LoRa for data transmission communication and Antares as a cloud service for storing data to be displayed on Android. The test results obtained the average error value for temperatures ± 0.8 °C, humidity ± 3.1 % RH, CO ± 10 ppm and CO2 ± 16 ppm. The results of sensor data are stored in the Antares cloud and displayed on Android.

Data mining merupakan proses analisis data menggunakan perangkat lunak untuk menemukan pola dan aturan (rules) dalam himpunan data. Data mining dapat menganalisis data yang besar untuk menemukan pengetahuan guna mendukung pengambilan keputusan. Dalam penelitian ini akan dibahas Association Rule sebagai salah satu fungsi data mining yang diimplementasikan menggunakan Algoritma Apriori. Akan dianalisis pula dua teknik penghitungan support di candidate generation pada Algoritma Apriori, yakni : K-way dan 2 Group-By pada tiga sampel dataset dengan atribut transaksi id dan item. Pada penelitian ini terlihat bahwa permasalahan penghitungan support di candidate generation merupakan bottleneck dari Algoritma Apriori dimana perbaikan Algoritma Apriori ditekankan pada candidate generation dan efektivitas dari Algoritma Apriori. Penelitian ini dilakukan pada RDBMS Oracle dengan memanfaatkan tools TKPROF untuk mengukur performansi query berdasarkan operasi I/O pada penghitungan support di candidate generation. Hasil penelitian membuktikan bahwa metode support counting K-way lebih baik daripada Two Group-by.Kata Kunci : Data Mining, Association Rule, Algoritma Apriori, candidate generation, K-way, 2 Group-By

Weather forecasting information is very crucial in decision making process regarding to activities and works, such as in the field of agriculture to determine initial growing season. Recently, climate change causes trouble in weather forecasting. In this paper, rainfall forecasting system using fuzzy system based on genetic algorithm (GA) is made. The data used within this research is taken from Indonesian Agency for Meteorology, Climatology and Geophysics (BMKG) for Kemayoran area, Jakarta. Those data include temperature, air pressure, rainfall, solar radiation, relative humidity, and wind speed. Based on experiment result, it can be concluded that the combination of GA and Fuzzy for Kemayoran weather data can produce prediction model with higher than 90% accuracy with several population size and crossover probability. This condition is highly affected by input data and conducted classification. Obtained model can be used in predicting rainfall class for the next day that divided into 4 class of no-rain or mild rain (<;=20 mm), moderate rain (<;=50 mm), heavy rain (<;=100 mm), and very heavy rain (>100 mm).

Pandemi COVID-19 (corona virus dease – 19) atau yang juga dikenal dengan nama virus Corona saat ini sedang melanda dunia. Terdapat lebih dari 3.900.000 kasus positif terinfeksi virus corona di seluruh dunia dan telah menelan korban jiwa lebih dari 270.000 jiwa. Indonesia sebagai negara dengan kepadatan penduduk nomor empat di dunia diperkirakan akan mendapat pengaruh yang sangat signifikan dan dalam periode waktu yang mungkin lebih lama dari negara lain karena tingkat disiplin yang masih kurang. Dampak pandemi ini ternyata tidak saja pada dunia kesehatan, tetapi juga sangat mempengaruhi seluruh aspek kehidupan masyarakat. Saat ini, masyarakat dianjurkan untuk melakukan social distancing, dimana kegiatan belajar, bekerja, dan beribadah dilakukan di rumah. Selain itu, anjuran tentang protocol kesehatan dari WHO (World Health Organization) seperti rajin mencuci tangan, menjaga kesehatan dan kebersihan serta selalu mengenakan masker apabila harus keluar rumah juga terus menerus digaungkan. Hal ini tentu berdampak pada kondisi ekonomi masyarakat secara umum, di mana banyak masyarakat dirumahkan karena perusahaan tempat mereka bekerja telah berhenti beroperasi baik secara temporer maupun permanen dengan adanya pandemi ini. Salah satu industri yang sangat terdampak oleh pandemi adalah industri pariwisata, dimana didalamnya terdapat sektor akomodasi wisata atau perhotelan. Sektor ini secara umum didominasi oleh perusahaan besar baik dalam negeri maupun milik asing, sektor perhotelan lumpuh beberapa bulan terakhir.

As a part of Customer Relationship Management (CRM), Churn Prediction is very important to predict customers who are most likely to churn and need to be retained with caring programs to prevent them to churn. Among machine learning algorithms, Extreme Gradient Boosting (XGBoost) is a recently popula