Journal of ICT Research and Applications

Strengthening INORMALS Using Context-based Natural Language Generation

Soni Yora, Ari Moesriami Barmawi — Wed, 31 Aug 2022 00:00:00 +0700

The noiseless steganography method that has been proposed by Wibowo can embed up to six characters in the provided cover text, but more than 59% of Indonesian words have a length of more than six characters, so there is room to improve Wibowo’s method. This paper proposes an improvement of Wibowo’s method by modifying the shifting codes and using context-based language generation. Based on 300 test messages, 99% of messages with more than six characters could be embedded by the proposed method, while using Wibowo’s method this was only 34%. Wibowo’s method can embed more than six characters only if the number of shifting codes is less than three, while the proposed method can embed more than six characters even if there are more than three shifting codes. Furthermore, the security for representing the number of code digits is increased by introducing a private key with the probability of guessing less than 1, while in Wibowo’s method this is 1. The naturalness of the cover sentences generated by the proposed method was maintained, which was about 99% when using the proposed method, while it was 98.61% when using Wibowo’s method.

Medium Access Control Protocol for High Altitude Platform Based Massive Machine Type Communication

Wed, 31 Aug 2022 00:00:00 +0700

Massive Machine Type Communication (mMTC) can be used to connect a large number of sensors over a wide coverage area. One of the places where mMTC can be applied is in wireless sensor networks (WSNs). A WSN consists of several sensor nodes that send their sensing information to the cluster head (CH), which can then be forwarded to a high altitude platform (HAP) station. Sensing information can be sent by the sensor nodes at the same time through the same medium, which means collision can occur. When this happens, the sensor node must re-send the sensing information, which causes energy wastage in the WSN. In this paper, we propose a Medium Access Control (MAC) protocol to control access from several sensor nodes during data transmission to avoid collision. The sensor nodes send Round Robin, Interrupt and Query data every eight hours. The initial slot for transmission of the Round Robin data can be either randomized or reserved. Analysis performance was done to see the efficiency of the network with the proposed MAC protocol. Based on the series of simulations that was conducted, the proposed MAC protocol can support a WSN system-based HAP for monitoring every eight hours. The proposed MAC protocol with an initial slot that is reserved for transmission of Round Robin data has greater network efficiency than a randomized slot.

Context-Aware Sentiment Analysis using Tweet Expansion Method

Bashar Tahayna, Ramesh Kumar Ayyasamy, Rehan Akbar — Wed, 31 Aug 2022 00:00:00 +0700

The large source of information space produced by the plethora of social media platforms in general and microblogging in particular has spawned a slew of new applications and prompted the rise and expansion of sentiment analysis research. We propose a sentiment analysis technique that identifies the main parts to describe tweet intent and also enriches them with relevant words, phrases, or even inferred variables. We followed a state-of-the-art hybrid deep learning model to combine Convolutional Neural Network (CNN) and the Long Short-Term Memory network (LSTM) to classify tweet data based on their polarity. To preserve the latent relationships between tweet terms and their expanded representation, sentence encoding and contextualized word embeddings are utilized. To investigate the performance of tweet embeddings on the sentiment analysis task, we tested several context-free models (Word2Vec, Sentence2Vec, Glove, and FastText), a dynamic embedding model (BERT), deep contextualized word representations (ELMo), and an entity-based model (Wikipedia). The proposed method and results prove that text enrichment improves the accuracy of sentiment polarity classification with a notable percentage.

Breast Cancer Diagnosis in Women Using Neural Networks and Deep Learning

Ojo Fagbuagun, Olaiya Folorunsho, Lawrence Adewole, Titilayo Akin-Olayemi — Fri, 09 Sep 2022 00:00:00 +0700

Breast cancer is a deadly disease affecting women around the world. It can spread rapidly into other parts of the body, causing untimely death when undetected due to rapid growth and division of cells in the breast. Early diagnosis of this disease tends to increase the survival rate of women suffering from the disease. The use of technology to detect breast cancer in women has been explored over the years. A major drawback of most research in this area is low accuracy in the detection rate of breast cancer in women. This is partly due to the availability of few data sets to train classifiers and the lack of efficient algorithms that achieve optimal results. This research aimed to develop a model that uses a machine learning approach (convolution neural network) to detect breast cancer in women with significantly high accuracy. In this paper, a model was developed using 569 mammograms of various breasts diagnosed with benign and maligned cancers. The model achieved an accuracy of 98.25% and sensitivity of 99.5% after 80 iterations.

Towards Enhancing Keyframe Extraction Strategy for Summarizing Surveillance Video: An Implementation Study

Fri, 23 Sep 2022 00:00:00 +0700

The large amounts of surveillance video data are recorded, containing many redundant video frames, which makes video browsing and retrieval difficult, thus increasing bandwidth utilization, storage capacity, and time consumed. To ensure the reduction in bandwidth utilization and storage capacity to the barest minimum, keyframe extraction strategies have been developed. These strategies are implemented to extract unique keyframes whilst removing redundancies. Despite the achieved improvement in keyframe extraction processes, there still exist a significant number of redundant frames in summarized videos. With a view to addressing this issue, the current paper proposes an enhanced keyframe extraction strategy using k-means clustering and a statistical approach. Surveillance footage, movie clips, advertisements, and sports videos from a benchmark database as well as Compeng IP surveillance videos were used to evaluate the performance of the proposed method. In terms of compression ratio, the results showed that the proposed scheme outperformed existing schemes by 2.82%. This implies that the proposed scheme further removed redundant frames whiles retaining video quality. In terms of video playtime, there was an average reduction of 27.32%, thus making video content retrieval less cumbersome when compared with existing schemes. Implementation was done using MATLAB R2020b.