Mahasiswa Teknik Informatika di Politeknik Negeri Malang dengan fokus pada pengembangan backend, optimasi database, serta integrasi IoT dan Machine Learning.
def introduce():
profile = {
"education": "Teknik Informatika - Politeknik Negeri Malang",
"passion": ["Backend Development", "Database Optimization", "IoT", "Machine Learning"],
"philosophy": "First, solve the problem. Then, write the code."
}
return profile- Email: 2341720088@student.polinema.ac.id
- Instagram: @not.samiddd
const technicalSkills = {
languages: ['PHP', 'Python', 'JavaScript', 'Java', 'Dart'],
frameworks: ['Laravel', 'TensorFlow', 'Keras', 'Flutter'],
databases: ['MySQL', 'SQL Server'],
tools: ['Git', 'VS Code', 'Postman', 'Arduino', 'Jupyter']
};
SELECT skill_name, proficiency_level
FROM my_skills
WHERE category = 'Database Management'
ORDER BY proficiency_level DESC;
import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.layers import LSTM, Dense, Dropout
class MLEnthusiast:
def __init__(self):
self.frameworks = ['TensorFlow', 'Keras', 'Scikit-learn', 'PyTorch', 'Statsmodels']
self.libraries = ['NumPy', 'Pandas', 'Matplotlib', 'Seaborn', 'Plotly', 'Optuna', 'SciPy', 'Joblib', 'ect']
self.expertise = [
'Time Series Forecasting (ARIMA, LSTM, GRU)',
'Deep Learning (LSTM, GRU)',
'Clustering & Dimensionality Reduction (KMeans, DBSCAN, PCA)',
'Unsupervised Learning & Visualization',
'Statistical Analysis',
'Model Evaluation, Optimization, & Tuning',
'Data Preprocessing & Visualization'
]
self.currently_learning = ['xLSTM', 'GPT Architecture']
namespace App\Projects\MAGNET;
class InternshipRecommendation {
use RecommendationBasedonPreference, optimizeData;
public function getOptimalPlacement(Student $student): Recommendation
{
return $this->algorithm
->considerLocation($student->location)
->analyzeSkills($student->skills)
->matchWithCompanies()
->optimize();
}
}Stack: Laravel 10, Livewire, FLux UI, MySQL
Sistem manajemen magang dengan algoritma rekomendasi cerdas untuk penempatan mahasiswa secara optimal. Fitur utama mencakup rekomendasi berbasis preferensi pengguna dan optimasi penempatan berbasis data. Untuk menghasilkan rekomendasi yang lebih akurat, sistem memanfaatkan ROC (Receiver Operating Characteristic) sebagai evaluasi performa model klasifikasi, serta metode MULTIMOORA sebagai pendekatan multi-criteria decision making untuk menentukan penempatan terbaik berdasarkan berbagai faktor.
import tensorflow as tf
from keras.models import Sequential
from keras.layers import LSTM, Dense, Dropout
class IHSGForecaster:
def __init__(self):
self.model = self.build_lstm_model()
self.metrics = {
'MAPE': '1.33%',
'architecture': 'Optimized LSTM Neural Network'
}
def build_lstm_model(self):
model = Sequential([
LSTM(units=50, return_sequences=True),
Dropout(0.2),
LSTM(units=50),
Dense(units=1)
])
return modelStack: Python, TensorFlow, Keras
Model forecasting time series untuk IHSG menggunakan LSTM Neural Networks dengan hasil MAPE 1.33% dan arsitektur optimal.
from sklearn.cluster import KMeans, DBSCAN
from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
import pandas as pd
import numpy as np
class StreamlyticsNetflix:
def __init__(self, data):
self.data = data
self.kmeans = KMeans(n_clusters=5, random_state=42)
self.dbscan = DBSCAN(eps=0.5, min_samples=5)
def run(self):
X = (self.data.select_dtypes(include=np.number) - self.data.mean()) / self.data.std()
self.data['KMeans'] = self.kmeans.fit_predict(X)
self.data['DBSCAN'] = self.dbscan.fit_predict(X)
return self.dataStack: Python, Scikit-learn, Pandas, NumPy
Segmentasi pengguna Netflix menggunakan K-Means dan DBSCAN untuk mengelompokkan perilaku menonton dan preferensi genre.
public class CafePOS {
private MenuManager menuManager;
private InventorySystem inventory;
private SalesAnalytics analytics;
public Transaction processOrder(Order order) {
inventory.updateStock(order.getItems());
Transaction transaction = new Transaction(order);
analytics.recordSale(transaction);
return transaction;
}
}Stack: Java
Sistem POS untuk manajemen kafe mencakup menu, inventori, dan analitik penjualan.