Search

In data security, a technique is needed to secure data from experiments and attacks by cryptanalysts. The technique of securing data is also known as cryptography. In this research, it has been done to improve data security by combining the Hill Cipher Algorithm with the Caesar Cipher Algorithm. This process can be seen from the tests that have been carried out in this study. The result is in a different and sufficiently improved processing time both in terms of decryption and encryption. By combining the two cryptographic algorithms, it is known that message security is much better. It occurs because the encryption and decryption process of the message is carried out using 2 different keys. Based on the tests, it shows that the time of the encryption process with the decryption process on the $5\times 5$ matrix key is very different from using the $3\times 3$ matrix key, the difference is slightly different in time. It shows that the use of a larger matrix key affects the decryption process is very long and also influenced by other cryptographic algorithm processes. In this study, another cryptographic algorithm is the Caesar Cipher Algorithm.

Affine Cipher is the development of Classic Caesar cipher that multiplies plain text before shifting operation. Affine cipher has two parameters namely key a, and b. Key ‘a’ is multiplies the plain text. It must have an inverse with Great Common Divisor (GCD) from the number of characters. The Problems of Affine Cipher Algorithm is the number of characters available and the least possible of key ‘a’ that can be used, so it is considered to be a classic technique that is easy to hack. Generally, Affine Cipher is used to encrypt the plaintext of character ‘A to Z’ so that the number of keys ‘a’ is only 12 digits from 26 digits (n) is available. Development of affine had increased the key ‘a’ into 128 of 256 digits (n) with 8 bit of ASCII. Digraph Transform is the modification of text encryption. It able to square the value of n. Usually, Text is encrypted by one character. In Digraph Transform, text is encrypted by two characters. For two characters, multiplying integer of the first character by number of characters, then add integer of the second character.

The marsh frogs that lost their habitat will become pests that are very detrimental to the fish cultivators. A technological approach is mandatory to assure the fish ponds to always be free from the frogs' presence by detecting the frog sound as a sign of frog existence in the breeding pond. This research implemented Mel Frequency Cepstral Coefficients- Vector Quantization (MFCC-VQ) algorithm to identify the frog's sound. The captured sound signal features will be extracted using Mel Frequency Cepstral Coefficients (MFCC) algorithm. The extracted sound signal will be identified using Vector Quantization (VQ) algorithm. The result of this research is the further the distance of the microphone from the sound source and the noisier environmental conditions in the detection process, the smaller the accuracy percentage. This study's highest accuracy is 99.6% at a distance of 1 meter and 83.2% at a distance of 11 meters in normal circumstances. Through the test, it can also be concluded that the further distance of the microphone from the source, the smaller the percentages of specificity and sensitivity, and the slower the processing speed, although the difference in speed per meter is not too significant.

Text classification using a simple word representation with a linear classifier often considered as strong baselines to gain the best performances. However, a simple word representation like Bag of Word (BOW) has a deficiency of curse dimensionality, so it is only suitable for small datasets. BOW also needs some dependent pre-processing steps like stopwords-removal and stemming. Therefore, the BOW model cannot be implemented automatically because of the dependency in a specific language. On the other hand, deep neural network classifiers can eliminate the pre-processing prerequisite, but this model not efficient in time processing and need a large dataset for the learning process. It becomes a challenge for language that has limitation resources like Bahasa Indonesia. Another novel approach of text classifier is using the fastText model for text classification. This model can minimize pre-processing dependencies and more efficient in training time processing. However, there hasn't been much observation whether the fastText model outperformed the BOW model for small datasets. This paper aims to compare text classification using the TFIDF model as one of the BOW models with a fastText model for 500 news articles in Bahasa Indonesia. The result of this study showed both models gain an outstanding performance, which is 0.97 F-Score. The TFIDF model needs longer pre-processing stages and requiring more training time. Meanwhile, the fastText model only needs to tune some hyperparameters and get similar performance results to the TFIDF model. Based on this study, we can conclude that the fastText model is efficient text classification.

Given the rapid growth of data and the reduced implementation quality of data mining and pattern extraction techniques, the use of feature reduction has become an important challenge of data mining and pattern recognition. An important goal of data reduction techniques is to make the minimum effort and achieve the maximum efficiency of data selection for the implementation of data mining process. The two primary objectives of feature selection are to minimize the errors of the patterns identified in the reduced subset and minimize the number of features. The majority of available feature selection algorithms adopts a single-objective approach. This is the first paper focused on clustering used as the identifier of unsupervised hidden patterns. It is also focused on the principal component analysis (PCA) to analyze the values of the features. The goals of the new multi-objective feature selection problem are to minimize the coefficient of PCA, maximize the accuracy of k-medoids clustering, and minimize the number of selected features. Another innovation of this study was to select the best subset of features at the best performance by using the electromagnetism-like mechanism (EM) algorithm. The proposed method was tested on 14 standard UCI datasets. The results indicated the competitive advantage of this algorithm over other algorithms implemented to solve this problem.

Cryptography has an important role in the process of data security. One of the benefits of applying cryptography is creating a sense of security in hiding data without having to doubt how much data you have. LUC, El Gamal and RSA have different characters, like formatting key processes, encryption and decryption process. So we need an algorithm performance comparison. Steps taken include determining the public key and private key, encryption process, decryption process, and testing in terms of program implementation time using several different texts. Based on tests of the encryption process, the results show that the fastest algorithm is the RSA algorithm. Other than that, the fastest decryption process is the LUC algorithm.

This study comparing the performance of SAW and MOORA methods are in the decision-making process against the evaluation of teacher assistant performance. Then, applying Rank Order Centroid (ROC) is to overcome the process of weighting attributes in decision-making. Subsequently, the data has used by Teaching Assistant Evaluation obtained from UCI Machine Learning Repository, which has 151 instances, five attributes, and 1 class label with multivariate type dataset. The results of testing the calculation of SAW and MOORA methods, obtain the different results where A134 is the best alternative in the calculation of SAW and A132 is the best alternative in the calculation of MOORA. Afterward, if viewing based on running time, the execution process of the SAW method is 0.06 seconds,while the execution process of the MOORA method is 0.02 seconds. In this research, both methods get the same results in ranking, but base on running time, the MOORA method is faster than the SAW method.

This paper proposes and develops an Applying the fuzzy inference method by Mamdani, Tsukamoto and Sugeno. Author will produce a comparison in the final results for each method inthesame case. And this method will be tested on a design model in the process of determining or predicting the export price of a commodity to obtain an optimal profit from the sales of the export commodity. This model includes the prediction of the resale price of exported goods abroad. The process of determining the selling price is calculated using the Fuzzy fuzzyinference method by Mamdani, Tsukamoto, and Sugeno. The variables to be observed are the demand for goods, availability of goods in the farmers, and market price in the foreign countries. The output is an estimated resale price and the profit of each export commodity and the comparison of the selling prices using Mamdani, Tsukamoto, and Sugeno is 2.1% while Mamdani and Sugeno are only 1%after applying logical negation to the basic rules, it is applied to 1.6%. With this comparison, the writer will evaluate the rule base section of Tsukamoto. The results obtained in this study include the prediction model of the resale price of exported goods and the results of the comparison of the performance of the fuzzy interference byMamdani and Tsukamoto logic methods in optimization to provide a more optimal price.

Digital image processing is used to analyze images consisting of visual perceptions whose purpose is to manipulate, modify the image, improve the quality of the image and prioritize the special features contained in the image by using the special attributes of the image characteristics that can be grouped based on the similarity of the image characteristics with each other. One method used in image recognition from artificial neural networks is Learning Vector Quantization (LVQ). The application of the LVQ method for face recognition requires a feature segmentation process so that the feature extraction values obtained only cover the face, this stage is carried out using the Fuzzy C-Means and K-Means Clustering methods. The results of face recognition testing using the LVQ method and K-Means Clustering segmentation obtained an accuracy of 92.22% (training) and 72.5% (testing). Face recognition with Fuzzy C-Means Clustering segmentation obtained face recognition results of 95.78% (training) and 76% (testing). The LVQ-FCM method is better than the LVQ with KMeans, obtained training accuracy of 3.56% and 3.5% for network testing.

Backpropagation (BP) has long training time and slow convergence, i.e. in minimizing Mean Square Error (MSE). Adaptive Moment Estimation (ADAM) was employed to speed up training and to obtain rate of BP. Result shown that the minimum MSE obtained was 0.002479194 and 0.002281315 in of 1000 and 2000, respectively.

In daily life, humans do all activities that are dense, both heavy and light activities. Of course, it will require energy or energy to carry out all these activities. The energy needed by humans can be obtained through the consumption of food and beverages, including food and beverages containing alcohol. Ethanol in alcoholic food and beverages human consumption has been consumed since time immemorial with a variety of different uses. Consumption of large amounts of alcohol will cause someone to be drunk or drunk. In some foods and beverages that are on the market, many contain alcohol, even in small quantities. If alcoholic beverages are consumed continuously in excessive amounts, it can cause acute respiratory failure and death. Because ethanol can eliminate awareness, humans who consume it can do bad deeds that are not realized. Accidents that occur in driving are part of other implications of the abuse of alcohol use. Consumption of alcohol which is too much lowers human performance in driving, so increasing the risk of accident or reduce driver survival chances. About 40% of total deaths that occur in traffic are related to alcohol use. A system for detecting alcohol use is needed by drivers, with the aim of reducing this. This system uses a sensor-based MQ303A microcontroller ATmega328 with GSM module SIM800L. This device uses the programming language C and datalog stored on the server using internet communication.

Cane (Saccharum officinarumL.) is a plant that is used as the main raw material in the sugar industry. One of the factors that can cause the reduction of sugar cane production and inhibit the development of the sugar industry is the late-diagnosed of leaf stain disease in sugarcane crops that cause crop failure. It is quite often the case because of the limited number of service facilities for communication and also the high cost to be incurred if the sugar cane entrepreneurs want to conduct the inspection process of the crop. Therefore, this study has a goal to identify leaf stain disease in sugarcane plants. This research used the image of sugar cane leaves that have stain spots as input for the image processing process using the Speeded-Up Robust Features (SURF) method. The identification process of leaf stains is divided into three types of leaf stain disease, namely ring stains, rust stains, and yellow stains. In this study, 60 images were used as preliminary data and 30 images for the testing process. Following the conducted test, it can be concluded that the early identification process of leaf stain disease in sugar cane has an accuracy rate of 90%.

Images could display visual information more than those of text data. However, when transmitted and acquired through communication channels, those images are always spoiled with noises that will reduce the quality of the image. Noisy image could not provide good quality image for further image processing due to poor quality. In image processing, standard genetic algorithm steps could be used to enhance image quality. The purpose of this research is to deploy uniform crossover of genetic algorithm to reduce noise in order to produce better offsprings. In every noise type, the obtained value of Mean Square Error (MSE) and Peak Signal-to-Noise Ratio (PSNR) resulted in image noise reduction were calculated and analyzed to see how both values of MSE and PSNR in average will change. For this purpose, we conducted tests with Pc values of 0.2, 0.4, 0.6, and 0.8, each with 100, 200, 300, 400, 500, and 1000 maximum number of generations, respectively. Result shows that uniform crossover obtained the best performance in reducing erlang noise and the worst performance in reducing localvar noise on three categories of images.

Text is an element which provides information to the readers. However, not all text is informative, some are still in need to be processed to generate information. In text processing process, data is required to be inputted into the system. The input process will be easier if the text is already in digital form. The main issue is when the text is in the non-digital form such as in the form of image. This image should be converted into a form which recognized by the machine. Therefore, an approach is required to be able to identify the text on the images, in expectation to generate text that can be processed by the machine. The method proposed for this research to identify the text is Convolutional Neural Network. Before and after entering the identification process, the input image will go through several pre-processing and post-processing phases to select which text to be displayed as a result. The testing process used images of receipt taken at the distance of 10cm and 12 cm. The result showed the accuracy rates of the testing using images of receipt taken at the distance of 10cm and 12 cm are 95% and 85% respectively.

Nowadays, short message service is one of the most popular communication systems between individuals using cellular phones. Every SMS entering a person cellular phone should be considered as a private matter, therefore its privacy as well a security are very important and be kept secret. One popular technique in securing the confidentiality of a message is cryptography whereby a plain message is transformed into an encrypted text. In this paper, we propose a hybrid of two symmetric cryptography algorithms in order to secure messages to be sent on an Android device. Algorithm to encrypt and to decrypt the message is RC4 cipher, while the algorithm to encrypt and decrypt the RC4 key is Affine cipher. The sender firstly encrypts the message to be sent and then encrypts the key. Both the cipher text and the cypher key are sent to the receiver. The receiver should decrypt the cipher key before the ciphertext could be decrypted. An Android based application has been built to implement the proposed method and the result obtained showed that the two algorithms provide a consistent encryption result where the length of the message before being encrypted is always the same as the message obtained after decryption.

Steganography means embedding messages into other media intended to avoid unauthorized parties from intervening. In general, the message insertion process is performed sequentially starting from the first pixel to the last pixel or else being initialized from the outer edge of the cover media. Major drawback of sequential insertion is the lack of strong security as unauthorized parties could easily intervene with the hidden message. In order to obtain better security, a combination of steganography and cryptography has also become preferential. Thereby in this paper, an enhanced Advance Encryption Standard (AES) cryptography is applied to the message before it is inserted into a cover media. In order to enhance the steganography, each encrypted character is inserted into the cover media by generating highly random positions using Linear Congruential Generator (LCG) method. Experiments were performed by LCG insertion of 1 bit message on each LSB value for the RGB layer. Results obtained showed an average MSE of 0.01 and highest average peak-signal to noise ratio (PSNR) value of 71.00% for the stego images created.

Class imbalance is the main problem in classification because the classification process tends to misclassify minority class which is an interesting class in another class if the training process is done to a set of instances. This problem will result in the result obtained biased towards to the class with a large number of instances. Against a number of methods proposed to overcome this class imbalance problem. One good method is the Hybrid Approach Redefinition (HAR) Method which has the advantage in overcoming the problem of class imbalance with the number of small classifiers and also the data diversity is good. This study will use the HAR Method incorporated with Loss Factors to correct the classification of most classes based on the performance evaluation of each classifier based on the F-Measure and G-Mean values. The results showed that HAR Method with Loss Factors gave better performance value compared with HAR Method without Loss Factor.

Human has their limitation of recognizing the detail of an object and requires longer time to identify it, especially for identifying the teeth which is usually done by forensic dentist. Therefore, a method is required for tooth identification in dental panoramic radiograph image. In this research, we use multilayer perceptron with Levenberg-Marquardt backpropagation training algorithm, to identify molar and premolar teeth based on the region property of isolated teeth generated from the integral projections. Several image processing techniques are also implemented to overcome the low contrast of the dental panoramic radiograph image. The experimental results show that our proposed method can help the forensic dentist to identify the molar and premolar teeth and give 98.2143% of accuracy while testing 10 dental panoramic radiograph images (consist of 56 teeth) with 20 images (consist of 152 teeth) for training data.

Babylon Tower is a three-dimensional puzzle which consists of six discs that are arranged piled up. Each disc consists of six columns of small balls along the side in six kinds of different colors. Babylon Tower can be played by rotating and sliding it. The goal of the game of Babylon Tower is to sort each ball of the same color on the same column and sort the balls in each column based on the brightness of the color of the ball. There are two methods that can be used to find a solution of the game of Babylon Tower, namely disc by disc and column by column. The method proposed in this research is depth-first search column by column. In this research, it is shown that the proposed method is capable of finding step by step to reach a solution of the game of Babylon Tower.

One common approach in constructing fuzzy classification systems based on if-then rules is using grid-partition. However, how to choose a precise size of the grid structure is still a problem. If the size of the grid is too coarse, the accuracy will be low, whereas if the size of the grid is too fine, rules could not be generated since there will be no object related to its membership function. To overcome the fine grid structure, a distributed-fuzzy-grid technique had been suggested. Yet this technique still has a problem in term of the number of generated-rules which increase significantly on every iteration caused by simultaneous overlapping grid-structure. In this research, an adaptive distributed grid-partition is proposed to generate fuzzy rule(s). Using this method, the number of generated rules can be adapted according to the needs so that the accuracy of the system as well as the complexity of inference time can be managed appropriately. The experimental results show that the average accuracy of rules generated using the adaptive distributed grid-partition is 96.59% compared to 96.36% resulted by the distributed grid-partition. In addition, an average accuracy of 98.83% was resulted compared to 97.166 obtained by another method.

Crowd simulation is the simulation process of movement on a large number of agents in a virtual environment and simulated in the form of animation. The object's tranquility is not just a collection of some individuals but the crowd of objects illustrating how individual's movements can be affected by other individual movements in the crowd. It is necessary then to set the direction and velocity of the object as it moves. The purpose of this research is to simulate the multi agency of movement between objects by using ClearPath. The output generated from this simulation is the simulation process time and the number of collisions that occur during the simulation process. The results obtained from several trials of three simulation models show that ClearPath is capable of handling simulations that require multiple objects, ClearPath can direct objects to avoid static obstacles, increasing number of objects will enhance the number of collisions occurring and simulation time.

Backpropagation and Direction Feature Extraction (DFE) are proposed in this paper for Chinese chess character recognition. Backpropagation is a feed-forward neural network algorithm designed for learning by examples namely by calculating errors and updating weights in each epoch. DFE is a feature extraction method by iterating and calculating the directons surrounding each pixel in the image to obtain the features. In this research, Chinese chess characters are recognized to obtain the correct amount of each chess character in a package. Due to the complex contour, stroke and pattern of Chinese chess characters, Chinese chess characters are difficult to be recognized by new learners. Both Backpropagation and DFE performance are capable in recognizing Chinese chess characters with good accuracy of 98% for various sets and it is also robust from transition, brightness, image noise and rotation up to 60°.

This research aims to develop a system which can help radiologists to identify the symptoms of breast cancer, using Evolving Connectionist Systems (ECoS). Breast cancer identification is done by using Breast Imaging Reporting and Database System as a standard system. In this study, medical images will be enhanced by using computer image processing techniques. Then, the enhanced image will be classified, and the result will be given to the radiologist for further medical diagnosis. Region of Interest (ROI) Segmentation is applied in this system, followed by image enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE). For the extraction of textural features, Gray Level Co-occurrence matrix (GLCM)is applied. Then features parameter is employed to identify the ROIs as either masses or calcification and then classify them into three categories, they are normal, benign and malignant. Three layers Simple Evolving Connectionist Systems (SECoS) with sixteen features was proposed for classifying the marked regions into BI-RADS 2 (benign) or BI-RADS 5 (malignant). 75.00% sensitivity and 88.89% specificity is achieved on INbreast dataset. Wisconsin Breast Cancer dataset is also used in this paper, 96.20% sensitivity and 99.24% specificity is achieved.

One primary objective in solving the job shop scheduling problems is to minimize the makespan, which is a particularly hard combinatorial optimization problem. The problem has been known for years and a vast majority of researches had been focused to solve the problem using a variety of optimization methods such as the branch and bound (B&B). However, the B&B method is considered as only suitable for small and medium size problems due its prohibitive computational time. In this paper, we implement the B&B method using the disjunctive programming approach to obtain optimal solutions for job shop scheduling problem. The B&B program developed is tested on a set of benchmark data and the results obtain are compared to best known from the previous work. Based on the comparison, we conclude that the branch and bound algorithm is considerable as a solution tool for small, medium, as well as large job shop problems.