Face recognition occluded by occlusions, such as glasses or shadows, remains a challenge in many security and surveillance applications. This study aims to analyze the performance of various machine learning and deep learning techniques in face recognition scenarios with occlusions. We evaluate KNN (standard and FisherFace), CNN, DenseNet, Inception, and FaceNet methods combined with a pre-trained DeepFace model using three public datasets: YALE, Essex Grimace, and Georgia Tech. The results show that KNN maintains the highest accuracy, reaching 100% on two datasets (Essex Grimace and YALE), even in the presence of occlusions. Meanwhile, CNN shows strong performance, with accuracy remaining 100% on YALE, both with and without occlusions, although its performance drops slightly on Essex Grimace (94% with occlusion). DenseNet and Inception show a more significant drop in accuracy when faced with occlusion, with DenseNet dropping from 81% to 72% on Essex Grimace and Inception dropping from 100% to 92% on the same dataset. FaceNet + DeepFace excels on more large dataset (Georgia Tech) with 98% accuracy, but its performance drops dramatically to 53% and 70% on Essex Grimace and YALE with occlusion. These findings indicate that while deep learning methods show high accuracy under ideal conditions, machine learning methods such as KNN are more flexible and robust to occlusion in face recognition.

As the volume of motorbikes increases, the number of motorbike service outlets also increases. However, not all service places get customers equally, from the customer's side various variables really determine visits such as location, level of spare parts availability, level of service to consumers and price. Likewise, in terms of service owners, when opening a new service location, they need to pay attention to various variables such as proximity to residential areas, number of competitors, capacity of passing vehicles, and proximity to spare parts suppliers. To collaborate several influential variables to produce a decision regarding the right place, a method is needed that is capable of carrying out calculations to produce a ranking of locations that will have an influence. One method that can be offered is profile matching. This method performs by finding the difference between the weight value determined at the beginning and the input value for each location object. The ranking results of all location objects can be used as alternative locations for appropriate service locations..

Penilaian secara periodik terhadap driver perlu dilakukan, untuk mengevaluasi kinerja. Pelaksanaan evaluasi membutuhkan waktu sehingga evaluasi sering dilakukan ketika terjadi keluhan dari penumpang, memberikan efek perubahan yang sifatnya sementara juga, setelah keluhan teratasi maka driver maupun pimpinan divisi transportasi menganggap tidak akan terjadi lagi kejadian yang sama. Bentuk evaluasi seperti di atas seringkali hanya  dilakukan terhadap driver yang dikeluhkan penumpang.   Penilaian kinerja yang termodel dan menyeluruh terhadap semua driver, yang sifatnya periodik dengan Sistem Pendukung Keputusan berbasis Profile Matching mampu meminimalisir kejadikan yang dikeluhkan penumpang..