Claim Missing Document
Check
Articles

Found 16 Documents
Search

Penerapan Metode Waspas Untuk Efektifitas Pengambilan Keputusan Pemutusan Hubungan Kerja Nelly Khairani Daulay
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 2 No. 2 (2021): Januari 2021
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v2i2.2773

Abstract

Layoffs are the most feared thing for every employee.  There are many reasons behind a termination.  For example, the company is experiencing a decline in terms of revenue so it feels necessary for a reduction in employees.  Then the mistakes made by the employee itself such as criminal acts or mistakes in the work, or perhaps the personal desire of the employee himself due to personal reasons. But in the event of termination of employment, the leadership should be wise so as not to happen things that can interfere with the sustainability of the company. Because often the assessment given to employees is not subjective so it harms the employee itself. To overcome this, a decision support system is needed that can help the leadership to be able to take good policies. This decision-making system (SPK) requires a method in the process of completion. There are many methods that can be used one of them is the WASPAS method. The purpose of this research is to give an overview to the leadership in order to make good decisions so as not to harm employees. The results obtained by Karywan with the smallest value will be laid off. The smallest value is obtained by employee no. 4 with a value of 0.75
Klasifikasi Kematangan Buah Pinang (Areca catechu L.) Menggunakan Hybrid Deep Feature Fusion dan XGBoost Anggi; Nelly Khairani Daulay; Ahmad Sobri
Bulletin of Information Technology (BIT) Vol 7 No 2 (2026)
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v7i2.2864

Abstract

Areca nut (Areca catechu L.) maturity is one of the factors affecting harvest quality. Visual maturity identification still has limitations because it can be influenced by observer subjectivity and environmental conditions. This study aims to classify areca nut maturity levels using a Hybrid Deep Feature Fusion approach by combining ResNet50 and EfficientNetB0 as feature extractors with XGBoost as the classification algorithm. The dataset used in this study was a primary dataset consisting of 1,200 areca nut images categorized into three maturity classes: unripe, semi-ripe, and ripe. The research stages included image preprocessing, feature extraction using CNN models, feature combination through feature concatenation, classification using XGBoost, and performance evaluation using accuracy, precision, recall, F1-score, confusion matrix, and 5-Fold Cross Validation. The experimental results showed that ResNet50 + XGBoost and Hybrid Deep Feature Fusion + XGBoost achieved accuracy, precision, recall, and F1-score values of 100%, while EfficientNetB0 + XGBoost achieved an accuracy of 99.16%. These results indicate that CNN-based features are able to represent the visual characteristics of areca nut images in the dataset used. The Hybrid Deep Feature Fusion approach provides an analysis of feature combination from two different CNN architectures, although increasing the feature dimensions does not always improve evaluation performance when a single feature extractor is already capable of representing dataset characteristics effectively. Future research can be conducted by increasing dataset variations to evaluate the generalization capability of the method under more diverse environmental conditions.
Penentuan Kelayakan Penerima Bantuan Program Keluarga Harapan Menggunakan Algoritma Support Vector Machine Nys. Sinta Audina; Tri Hasanah Bimastari Aviani; Nelly Khairani Daulay
Journal of Computer System and Informatics (JoSYC) Vol 7 No 1 (2025): November 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i4.8064

Abstract

Technological developments, particularly in the field of machine learning, have had a significant impact on supporting data-driven decision making. One of the challenges faced in implementing PKH in Tiang Pumpung Kepungut Subdistrict, Musi Rawas Regency, is [A1] the process of determining aid recipients, which is still done manually. Data is still manually recorded into Excel based on data obtained during the population census. This often causes errors and mistakes during the aid distribution process. To overcome this problem, this study proposes the use of the Support Vector Machine algorithm in the PKH beneficiary classification process. Support Vector Machine is an effective classification method for handling complex and non-linear data with a high degree of accuracy. This study aims to develop a Support Vector Machine-based system to improve efficiency, accuracy, and transparency in the selection process for determining the eligibility of aid recipients. A total of 250 PKH data sets were successfully obtained. The data obtained or collected included several variables, namely name, age, number of family members, occupation, income, number of dependent children, and status. The data was then divided into two sets: 80% for training and 20% for testing from a total of 250 data points. After cleaning the data, the number of data points became 244, with 195 for training and 49 for testing. The results of this study showed that 39 families were eligible to receive assistance and 10 families were not eligible. It is hoped that the resulting system can serve as an innovative solution to support more targeted social assistance distribution in the region.
NETWORK SECURITY DETECTION SYSTEM ON DAPODIK SERVER AT SMPN I MUARA KELINGI AGAINST SNIFFING ATTACKS Nelly Khairani Daulay; Resha Purnama Sari; Asep Toyib Hidayat; Phito Prima Sanjaya; Anisya Apriliana
Journal Renewable Energy, Electronics and Control Vol 3, No 1 (2023): JURNAL JREEC
Publisher : Department of Electrical Engineering, Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.jreec.2023.v3i1.4552

Abstract

Information technology (IT) has been applied to various sectors, including industry, government, education and health. However, technological sophistication is also accompanied by threats in terms of data security. For this reason, a system is needed that can secure the data, where attacks on data often occur from networks connected to the internet. The world of education today is also very dependent on technological sophistication, especially in data storage. One that utilizes this technology is SMPN I Muara Kelingi. The problem currently faced is the lack of a data security system on the Dapodik Server at SMPN I Muara Kelingi. The attack that can attack the network is in the form of a sniffing attack. The purpose of making this system is so that the data or information contained in the system cannot be accessed by unauthorized persons and to prevent damage to the system. By using the Security Policy Development Life Cycle (SPDLC) and using Snort as a tool to detect packet sniffing attacks, the school can quickly detect attacks that occur on the school Dapodik Server.
System Informasi Penjualan Online Berbasis Web Menggunakan Metode CRM(Customer Relationship Management) Pada Perusahaan Showroom Mobil Intan Mobilindo Nelly Khairani Daulay; Sugallu Hangga Reksa; Budi Santoso
Journal Renewable Energy, Electronics and Control Vol 4, No 2 (2024): JURNAL JREEC
Publisher : Department of Electrical Engineering, Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.jreec.2024.v4i2.6637

Abstract

PT. Intan Mobilindo yang berada di Lubuklinggau bergerak di bidang jual beli kendaraan mobil masih menggunakan metode manual dalam melakukan jual belinya,tidak memiliki aktifitas atau strategi khusus yang menangani pemasaran, pemasaran produk dilakukan secara konvensional dengan cara pelanggan memberikan informasi mengenai tempat, keistimewaan dan produk ke calon pelanggan lain. E-commerce merupakan sebuah media online yang digunakan untuk aktifitas yang berkaitan dengan penjualan, pembelian, dan pemasaran barang atau jasa. E-commerce melibatkan kegiatan teknologi internet lainnya seperti transaksi dana elektronik atau yang biasa disebut dengan m-banking, pertukaran data elektronik, sistem pengumpulan data otomatis, dan sistem inventori otomatis. Tujuan penelitian ini adalah membuat system informasi penjualan online berbasis web menggunakan CRM (Customer Relationship Management) pada perusahaan showroom mobil intan mobilindo. Dengan adanya sistem ini akan memberikan solusi alternatif yang dapat menunjang kegiatan bisnis perdagangan serta dapat dijadikan alat pemasaran produk dan pengelolahan data penjualan. Sistem yang telah dibuat akan dikembangkan menggunakan metode air terjun (Waterfall) sering juga disebut metode sekuensial linier, menyediakan pendekatan alur hidup perangkat lunak secara sekuensial atau terurut di mulai dari analisis, desain pengodean, pengujian dan tahap pendukung. Penelitian ini menghasilkan sebuah website yang dapat membantu pihak PT. Intan Mobilindo dalam memasarkan barangnya dengan lebih efisien dan cepat, sehingga membantu dalam meraih pasar produk digital dan membantu dalam mendata customer untuk melakukan analisis pasar.
DETECTION OF PING FLOOD ATTACKS ON CCTV SERVERS Nelly Khairani Daulay; Dani Raisman Raisman; Refdi Andri Andri
Journal Renewable Energy, Electronics and Control Vol 3, No 1 (2023): JURNAL JREEC
Publisher : Department of Electrical Engineering, Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.jreec.2023.v3i1.4520

Abstract

The development of information technology, especially computer networks, allows the exchange of information that is easy, fast, and increasingly complex. Computer network security must be considered in order to maintain the validity and integrity of data and information residing in the computer network. The problem that arises in the CCTV control center is that there is no security against the detection of attacks that can occur at any time, for example a ping flood attack. Ping flood itself can be interpreted as a simple denial of service attack in which the attacker floods the victim with "echo request" (ping) packets in the ICMP protocol. To overcome the problems faced by the Lubuklinggau City Police control center in carrying out CCTV server security, the solution offered is to build an Intrusion Detection Server (IDS). IDS itself can read incoming and outgoing data packets automatically which will provide a report (log) to the network administrator. One of the most widely used IDS tools is Snort. Snort has several advantages compared to other IDS software, including source code that is small in size, compatible with many operating systems, fast in detecting network attacks, easy to configure and is open source.