MIM (Mobile Instant Messaging) Classification using Term Frequency-Inverse Document Frequency (TF-IDF) and Bayesian Algorithm |
Author : Kashaf-u-Duja, Muhammad Bux Alvi, Tariq Jameel Saifullah Khanzada, Nisha Kumari |
Abstract | Full Text |
Abstract :The focus of the study is based on binary sentiment classification on aspect level to develop a hybrid sentiment
classification framework of WhatsApp MIMs (Mobile Instant Messages). It has been carried out into two phases
i.e. training phase and testing phase. The training phase, 75% data is used for training dataset. Pre-processing
techniques like tokenization, removing stop words, case normalization, removing punctuation and stemming are
applied to acquire cleaner dataset to be used as input. The output is sent to the classifier after applying TF-IDF
for feature weighting. In the second phase, the classifier is trial with 25% testing dataset. Bernoulli’s Naïve
Bayesian classifier which is an improved form of traditional Naïve Bayesian classifier is used to classify
sentiments. There are 417 messages in total where 244 and 173 are classified as positive and negative
respectively. The proposed model has achieved satisfactory results up to 81.73% in comparison to base-line
classification model by getting 12 points higher accuracy i.e. 69.23%. |
|
Analysis and Implementation of Solid-State Relays in Industrial application For Instantaneous Current Supply |
Author : Fawad M.Memon Engr.Noor Nabi Shaikh, Engr. Nizamuddin Channa Engr. Shafqat Hussain Memon |
Abstract | Full Text |
Abstract :There are many applications and circumstances where switching devices are required for proper operation,
controlling and isolating the high power and low power systems. The most widely used switching devices are
electromechanical relays and solid state relays. In this work, analysis and implementation of solid state relays over
electromechanical relays with respect to instantaneous current supply inindustrial application is conducted and
compared. For this purpose, an experimental setup is arranged for switching operation of electromechanical relays
and solid-state relays. |
|
IoT based Environmental Monitoring and Control System |
Author : Ghulam Rubab Mirza, Mukhtiar Ahmed Mahar, Abdul Sattar Larik ,Abdul Razzaque Jawad, Ghulam Fiza Mirza |
Abstract | Full Text |
Abstract :IoT plays a major role in collecting the information from the sensing unit enclosing our environment due to
alterations in the climate which led to the significance of environmental monitoring. This Paper presents a
development of real time environmental monitoring and control system by utilizing Node MCU, DHT11 sensor,
ACS712 current sensor, Thing Speak (Open IoT analytics service) and Blynk application. The main task of
monitoring parameters (Humidity, temperature and power consumption) with real time sensors is done by Thing
Speak continuously which has API (Application programming Interface) for gathering sensed data and enabling
users to observe the monitored data in graphs for an interval of every 15 seconds |
|
Anti-Smog Radar Application for Vehicles |
Author : Ghulam Fiza Mirza, Abdul Razzaque Jawad,Hyder Bux Mangrio, Ghulam Rubab Mirza |
Abstract | Full Text |
Abstract :Smog is regarded as a dangerous situation for vehicles as the visibility of human fails and a person cannot
drive smoothly and safely which can lead to severe accidents and routine disturbances. Hence, “Anti-Smog
Radar Application for Vehicles” is proposed using Internet of Things technology which ensures the smooth flow
of vehicles in smog and prevents accidents in time and cost-efficient manner by detecting and displaying the
front objects with their important information (distance, position, velocity and size) on smart phone used by
authenticated drivers. The radar application controls the hardware system to be deployed on vehicles through
which the user can start, stop and set the hardware in particular direction. The hardware contains NodeMcu
(Microcontroller with built-in Wi-Fi), Ultrasonic sensor and servo motor. |
|