As the prevalence of diabetes mellitus rises, more families are being impacted. Most diabetics don't know much about their health situation or the risks they face before getting a diagnosis. A unique data mining-b...
详细信息
Due to an increase in the load of network, load balancing service, i.e., a service that gives an equal volume of each task assignment to each of the servers in data centers, it is usually performed by the specialized ...
详细信息
The faculty of computerscience, Universitas Brawijaya (Filkom UB) is committed to providing quality services for the users especially internal and external stakeholders, one of which is through the HaloFilkom service...
详细信息
ISBN:
(纸本)9798350379914
The faculty of computerscience, Universitas Brawijaya (Filkom UB) is committed to providing quality services for the users especially internal and external stakeholders, one of which is through the HaloFilkom service. HaloFilkom services have limitations in terms of time. HaloFilkom services are not available 24 hours due to limited working hours. Questions asked by users are not answered directly. This weakness in the HaloFilkom system can be overcome by using a chatbot system. Chatbot is an interactive system that works with natural human language and can work 24 hours. Thus, the current study explores the basic chatbot model by classifying the Q&A in the closed domain knowledge. The dataset in this research is in the form of pairs of questions and answers regarding various topics at the Filkom UB. The knowledge is preprocessed using text preprocessing which includes case folding, tokenization, padding, and tensorization. One of the chatbot models is a generative model. Creating a generative chatbot model can be done using the Seq2Seq model mechanism which consists of an encoder and decoder. The model created consists of four different architectures, namely a model with an LSTM encoder without attention and with attention and a BiLSTM model encoder without attention and with attention. Hyperparameter tuning was conducted to obtain the best hyperparameter combination. The experiment results show the best hyperparameter combination obtained is hidden size 448, drop out rate 0.5, learning rate 0.001, batch size 64, and teacher force 0. The model with the best loss is obtained with a BiLSTM encoder architecture without an attention mechanism with a train loss of 0.120. The model with the highest BLEU Score was obtained by a model with a BiLSTM encoder architecture without an attention mechanism with a BLEU Score of 0.8587 on the training data. Testing using prompt testing obtained an average BLEU Score of 0.3745 on the BiLSTM encoder without an attention mechanism mo
An intelligent robotic vehicle with an ultrasonic sensor that can avoid obstacles in its path is the research idea. This sensor recognizes obstructions, permitting the vehicle to perform activities like halting, turni...
详细信息
Crime is a widespread societal issue that has a negative impact on people's standard of living and the nation's prosperity. It's a major consideration for potential residents and tourists alike when decidi...
详细信息
Earth observation (EO) data have seen a constant surge in volume, necessitating efficient storage, retrieval, and sharing mechanisms. Cartographic projections play a vital role in transforming spheroidal surface data ...
详细信息
Nowadays, traffic sign recognition is disrupted through various external factors such as chromatic aberration, geographical separation, and brightness of lights. This eventually poses possible safety hazards during na...
详细信息
The detection and tracking of changes in the progression of GI disease using endoscopic video analysis remains difficult due to temporal changes and image complexity. Proper models of prediction are critical in diagno...
详细信息
Open data initiatives have resulted in a large amount of data being published on open data portals. In order to make published data more accessible these portals provide search mechanisms based on metadata like catego...
详细信息
Fine-Tuning of large language models is often demanding in terms of computational resources and memory. Consequently, there is a need to explore new methods that can effectively fine-Tune these models without compromi...
详细信息
暂无评论