Identifying the identity of a prisoner in a detention cell, through facial recognition automatically is a big, exciting problem and there are many different approaches to solve this problem because it must detect multiple faces (multi-face). Especially in uncontrolled real-life scenarios, faces will be seen from various sides and not always facing forward, which makes classification problems more difficult to solve. In this research, one method is combined deep neural networks that is Convolutional Neural Networks (CNN) and Haar Cascade Classifier as real-time facial recognition, which has proven to be very efficient in face classification. Methods are implemented with assistance library Open-CV for multi-face detection and 5MP CCTV camera devices. In preparing the architectural model Convolutional Neural Networks Do configuration parameter initialization to speed up the network training process. Test results on 51 test data using constructs Convolutional Neural Networks VGG16 models up to a depth of 16 layers of convolution layers with input from the extraction of the Haar Cascade Classifier resulting in facial recognition system performance reaching an accuracy rate of about 87%.

One of the digital data is a document. Documents can be easily copied and deleted. Anyone can retype or copy parts of the document. In this paper will detect text similarity. The more similarity of words there is the more indicated the document is plagiarism. Winnowing algorithm performs the calculation of hash values of each k-gram. This method improves the search time with more accuracy in the detection process. All data selected hash values will be fingerprints of a document. Fingerprint will be used as a basis for comparing similarities between text data. The fingerprint value of the winnowing process for each document will be matched by using the Jaccard Coefficient to measure the similarity of the text. In this paper results show that the adjustment of the k-gram and window values can affect the final result of the similarity percentage value. The smaller the k-gram value, the greater the percentage value.

Malaria is a disease caused by the Plasmodium falciparum parasite carried by female Anopheles mosquitoes. This disease is still a severe threat in eastern Indonesia which is an endemic area of Malaria. A data-driven computer-aided diagnostic approach can be an innovative solution. From the experiment results using the Pre-trained Deep Convolutional Neural Network algorithm that was trained with the transfer learning method, the GoogLeNet model was able to achieve a detection accuracy of 93.89%. In comparison, the ShuffleNet V2 model gained 95.20% accuracy with training times three times faster than GoogLeNet.

Healthy and superior sperm is the main requirement for a woman to get pregnant. To find out how the quality of sperm is needed several checks. One of them is a sperm analysis test to see the movement of sperm objects, the analysis is observed using a microscope and calculated manually. The first step in analyzing the scheme is detecting and separating sperm objects. This research is detecting and calculating sperm movements in video data. To detect moving sperm, the background processing of sperm video data is essential for the success of the next process. This research aims to apply and compare some background subtraction algorithms to detect and count moving sperm in microscopic videos of sperm fluid, so we get a background subtraction algorithm that is suitable for the case of sperm detection and sperm count. The research methodology begins with the acquisition of sperm video data. Then, preprocessing using a Gaussian filter, background subtraction, morphological operations that produce foreground masks, and compared with moving sperm ground truth images for validation of the detection results of each background subtraction algorithm. It also shows that the system has been able to detect and count moving sperm. The test results show that the MoG (Mixture of Gaussian) V2 (2 Dimension Variable) algorithm has an f-measure value of 0.9449 and has succeeded in extracting sperm shape close to its original form and is superior compared to other methods. To conclude, the sperm analysis process can be done automatically and efficiently in terms of time.

Two factors that cause male infertility include spermatozoa and nonspermatozoa factors. To discover infertility caused by spermatozoa factor, sperm analysis can be conducted. One of the analysis processes is analyzing the morphology (that is related to the shape of head, neck, and tail) of spermatozoa. The analysis of sperm abnormality is based on the current morphology by observing and calculating the normal shape of sperms manually. Therefore, a system to analyze spermatozoa automatically is required so as to provide essential information regarding sperm condition accurately and quickly. The contribution of this research is to classify spermatozoa automatically and distinguish objects that are not spermatozoa. The novel element of this research is the analysis of sperm morphology based on microscopic videos of spermatozoa by comparing it with the previous researches with images as input data. Hence, what was conducted in this research is automation in analyzing spermatozoa with microscopic video or moving images of spermatozoa as the input data. The research method was initiated with a preprocessing procedure, which included extracting video into images, erosion and dilation operations. It was followed by the process of object segmentation and detection based on edge line, color, and color intensity using contour detection, feature extraction based on eccentricity and Equivalent Circular Diameter (ECD), and finally, classification using decision tree with accuracy result of 83.81%.