Machine learning entails building a model that has been trained on some training data and can subsequently process more data to produce predictions.
For machine learning systems, various types of models have been utilized and investigated. An artificial neural network is a model built on a set of connected units or nodes known as “artificial neurons,” which are roughly modeled after the neurons in a biological brain. Each link, like the synapses in a human brain, can send information, or a “signal,” from one artificial neuron to the next. When an artificial neuron receives a signal, it can process it and then send it to other artificial neurons.
An artificial neural network approach’s original goal was to solve problems in the same way a human brain would. However, as time passed, attention shifted to specific tasks, leading to biological deviations. Even medical diagnosis is just a few of the activities that artificial neural networks have been utilized for. One of the predictive modeling methodologies used in statistics, data mining, and machine learning is decision tree learning, also known as induction of decision trees. It goes from remarking on something (represented by the branches) to inferences about the item’s goal value using a decision tree (as a predictive model) (represented in the leaves). A decision tree is a straightforward way of categorizing examples. Assume that all of the input features have discrete domains that are finite in size, and that there is only one target feature termed “classification” in this section. Each element of the categorization domain is referred to as a class. A decision tree, also known as a classification tree, is a tree in which each internal (non-leaf) node has an input feature labeled on it.
Support-vector machines, commonly referred to as support-vector networks, are a group of supervised learning algorithms for classification and regression. Support-vector machines training method creates a model that predicts whether a fresh case will fit into one of the categories of two categories given a set of training examples that are individually labeled as belonging to one of two categories. When data is unlabeled, supervised learning is impossible, hence an unsupervised learning strategy is necessary, in which the data is clustered naturally into groups and new data is mapped to these groups.
Regression analysis is a broad term that refers to a number of statistical techniques for estimating the link between input variables and their corresponding output variables’ characteristics. Linear regression is the most frequent type, in which a single line is generated to best match the available data using a mathematical criterion such as ordinary least squares. Regression analysis is a tool that can be used to identify causal relationships between independent and dependent variables in specific scenarios. Importantly, regressions reveal correlations between a dependent variable and a group of independent variables in a given dataset by themselves. A researcher must carefully demonstrate why existing correlations have predictive strength in a new environment, or why a causal interpretation of a relationship between two variables before using regressions for prediction or inferring causal relationships. In Bayesian networks, efficient algorithms can do inference and learning. Dynamic Bayesian networks are Bayesian networks are used to model variable sequences. (such as speech signals or protein sequences). Bayesian networks are directed acyclic graphs with nodes that represent variables in the Bayesian sense: observable quantities, hidden variables, unknown parameters, or hypotheses. Nodes that are not connected (no path connects one node to another) represent variables that are conditionally independent of each other; Nodes that are not connected (no path connects one node to another) represent variables that are conditionally independent of each other. A Bayesian network may be used to respond to probabilistic questions concerning its variables and relationships since it is a comprehensive model for them. When other variables (evidence variables) are seen, the network can be utilized to update knowledge of the status of a subset of variables. Probabilistic inference is the process of calculating the given variable’s posterior distribution evidence
Models of Machine Learning
PEC Chairman visits AT, assures his support for local engineering initiatives
Alsons develops
new variant of ventilator
Engr. Najeeb Haroon, the Chairman of the Pakistan Engineering Council (PEC) visited Alsons Technologies (AT) in Karachi last week.
The intent was crystal clear that the council is always ready to support every initiative that could bolster the engineering industry in Pakistan.
His visit coincided with yet another achievement of AT that has developed a prototype of different kind of ventilator ready to go through the registration process of the council.
This machine has been developed in association with Exovent – a UK-based non-profit organization comprising senior clinicians and professors from some of the UK’s top medical universities and hospitals.
Chairman Alsons Group Abdul Rehman Allana who hosted Engr Haroon says this low-cost high-tech device can be critical to saving lives affected by respiratory failure.
AT, a subsidiary of Alsons Group has the prestige to be the only Pakistani company that has produced three locally manufactured biomedical devices in Pakistan.
AT has successfully manufactured and eventually introduced into the market a High-Flow Nasal Oxygen (HFNO)/ Continuous Positive Airway Pressure (CPAP) machine namely Alnno Ventura, and its ventilator under the approval process of the Drug Regulatory Authority, Pakistan (DRAP). The company has announced its ICU ventilator, the AlnnoVent AVB100 has successfully completed 285 hours on a single patient at Jinnah Hospital in Lahore. The patient has been connected to our device 24/7 since 16th May 2022.
“This is in addition to 139 hours of clinical trials conducted previously on 26 different patients’, Akbar Allana, a director of Alsons Group told Engineering Review.
Engr. Najeeb Haroon and Abdul Rehman Allana agreed that the local initiatives should be supported so that the engineering industry may be able to produce Pakistan-made products.
Mr. Allana assured Chairman PEC of his complete support in the council’s initiatives for the training of fresh engineers through the internship program and also would bolster its liaison with the academia for research and development of engineering products in Pakistan.
Alsons Group is liaising with several Pakistani universities including NUST, MUET, Jamshoro, Biomedical Institute LUMS, DUET, Karachi, SAU, Tando Jam, etc. – By Manzoor Shaikh
PSDP goes dry in full; no money for release in last quarter
Ahsan Iqbal’s May 30th Tweet spoke loudly about the state of our economy and cash availability. The situation has aggravated to a point where the country’s Public Sector Development Program (PSDP) will go completely dry in the last quarter of the current fiscal year.
The Planning and Development (P&D) minister tweeted: Let me share with you the extent & state of the damaged economy we have inherited. For the first time in the country’s history, the Ministry of Finance has notified that there will be zero release of funds for the development budget during the last quarter.
Worth Rs.900 billion PSDP that had already undergone a huge cut of Rs.400 billion during Imran Khan’s government had little over Rs.466 billion for the period spread over July to March (2021-22) whereas the authorization stood at Rs.603 billion.
The P&D figures show the Finance Department released only 51.8 percent of the total budgeted amount of the program for the period July-March.
During July-March 2021-22 only 51.8 percent of the total budgeted PSDP was released while authorization was Rs136.9 billion less than what was actually disbursed in the July-March period.
Even the federal ministries and their departments were given Rs.45 billion less than what they were supposed to get for their expenditures.
Interestingly enough, the Power Division got Rs39.65 billion against its authorization of Rs12.27 billion, 223 percent more than it was supposed to get. The water Resources Division spent Rs4.8 billion which is also 7.5 percent more than the actual authorization.
The rest of the divisions are here.
Reko Diq to start producing gold and copper by 2027
Barrick Gold Corporation says the company would convert Pakistan’s Reko Diq into a world-class mine and the company would start production of gold and copper by 2027.
The chief executive officer (CEO) of the Canada-based mining firm said this week that agreements underlying the framework agreement were being finalized by teams from Barrick and Pakistan.
The Reko Diq project in Pakistan’s southwestern Balochistan province, which hosts one of the world’s largest undeveloped copper and gold deposits, was suspended in 2011 after Pakistan denied Barrick Gold and Chile’s Antofagasta a license to develop it.
An agreement reached between the Government of Pakistan, the provincial government of Balochistan and Barrick earlier this year provides for the reconstitution and restart of the project, which has been on hold since 2011. It will be operated and owned 50 percent by Barrick, 25 percent by the Balochistan government and 25 percent by the Pakistani state-owned enterprises.
“The definitive agreements underlying the framework agreement are currently being finalized by teams from Barrick and Pakistan,” Barrick CEO Mark Bristow said at a press conference in Islamabad.
“Construction of the first phase will follow that with the first production of copper and gold expected in 2027-28.”
Bristow said Barrick would bring capital and technology to convert Reko Diq into a world-class mine and transform Balochistan.
“The project will bring in $10 billion investment in Pakistan, out of this, $4 billion in the first phase till 2027, then $3 billion during the second phase and another $3 billion in the third phase,” he said.
Subject to the updated feasibility study expected in two years, Bristow said, Reko Diq is envisaged as a conventional open pit and milling operation, producing a high-quality copper-gold concentrate.
“It will be constructed in two phases, starting with a plant that will be able to process approximately 40 million tonnes of ore per annum which could be doubled in five years,” he said.
With its unique combination of large-scale, low strip and a good grade, Reko Diq will be a multi-generational mine with a life of at least 40 years, according to the Barrick CEO.
During the negotiations, he said, the Pakistani government and Barrick agreed that Balochistan and its people should receive their fair share of the benefits as part of the Pakistan ownership program.
“The project will have 100 percent Pakistani workers who will be first trained by Barrick for the mining job,” Bristow said. “During the peak construction, the project is expected to employee 7,500 people and once in production it will create 4,000 long-term jobs.”
Pakistan’s Finance Minister Ismail said the development of Reko Diq represented the largest direct foreign investment in Balochistan and one of the largest in Pakistan.
“Like Barrick, we believe that the future of mining lies in mutually beneficial partnerships between host countries and world-class mining companies,” Ismail was quoted as saying in a Barrick statement.
“The Reko Diq agreement exemplifies this philosophy and also signals to the international community that Pakistan is open for business.”
The finance minister said his government was looking forward to Barrick Gold’s investment in the copper and gold mine. “I believe this investment is going to be transformational for Balochistan and Pakistan,” he said on Twitter.
Bristow said multiple social welfare programs for the people of Balochistan would be initiated in education, healthcare and food security as well as for the provision of potable water in a region where groundwater has a high saline content.
“This includes an upfront social development spend of up to $3 million in year one and up to $7 million in year two during the feasibility study update,” the Barrick CEO said.
“One percent of capital during construction phase [and] 0.4 percent of revenue thereafter on an annual basis would also go to the social welfare of the local public.”
He said the unique feature of the agreement was that the Balochistan government would start receiving royalty of the project before the start of operations.
“The Balochistan government will get up to $5 million in the first year, $7.5 million in the second year and $10 million annually from the third year till commercial production is achieved,” Bristow said.
“The Reko Diq agreement also signals to the international community that Pakistan is open for business,” he added
Wind Turbine: Environmental Impact and Recycling Engr. Dr. Muhammad Nawaz Iqbal
Onshore wind farms can have a considerable impact on the landscape because they often require more land than other power plants and must be erected in remote and rural regions. Wind turbines also produce noise, which can reach 45 decibels (dB) at a residential distance of 300 meters (980 feet); however, at 1.5 kilometers (1 mile), most wind turbines become inaudible. Loud or continuous noise causes stress, which can lead to diseases. When correctly installed, wind turbines produce no noise that is harmful to human heal.
Wind power does not require water for continuous operation and emits very few emissions that are directly related to the generation of electricity. Wind turbines produce small amounts of carbon dioxide, carbon monoxide, Sulphur dioxide, nitrogen dioxide, mercury, and radioactive waste when they are disconnected from the electric grid, in contrast to fossil fuel and nuclear energy station fuel generation, respectively.
Neodymium is utilized in the creation of permanent magnets, which are employed in some wind turbines. Concerns over pollution from the mining of this rare-earth element, which is mostly exported by China, have motivated government action in recent years, as well as international research efforts to improve the extraction process.
Blades of modified wind turbines are composed of composite plastic/fiberglass designs with a service life of fewer than 20 years. There was no cost-effective technique or There is a market for these old blades to be recycled. as of February 2018, hence the most prevalent disposal method is to transport them to landfills. Other possibilities Included in the disposal of the blades are incinerating them or grinding them into powder, but both of these techniques are not only costly but also inefficient and waste energy. Although the foundation of the building, which is normally composed of reinforced concrete, and the blades cannot be recycled, up to 80% of the wind turbine construction can be recycled. Alternatively, these turbine structural components that are difficult to recycle into new turbines might be repurposed and utilized in various ways. The blades could potentially be recycled into building materials and structural components, such as aggregate in concrete utilizing composite material made from the blades. According to existing research, turbine blades could be successfully poles that have been reused as electrical transmission poles because their strength and structural stability are comparable to that of traditional materials. Roofs for small houses have been made from blade sections., and these structures exceed building code standards. This could prove to be a practical solution to reuse blade components without requiring considerable processing.
Wind farms are frequently constructed on land that has already been cleared. When compared to coal mines and coal-fired power plants, wind farms require minimal vegetation clearing and ground disturbance. The terrain can be restored to its previous state if wind farms are decommissioned. Wind-energy proponents argue that just 1% of the land is utilized for foundations and access roads, leaving 99 percent of the land available for agriculture. The base for a wind turbine requires approximately 200–400 m2.
Farming and cattle grazing are still possible on the property. Wind farms have little impact on cattle. Livestock will graze right up to the base of wind turbines and will often graze right up to the base of wind turbines and utilize them as rubbing posts or for shade, according to international experience.
The impact of wind energy on birds is complicated, as they can fly into turbines directly or have their habitats harmed indirectly as a result of wind development.
Wind farms may have an impact on the weather in their near surroundings. The turbulence created by spinning wind turbine rotors enhances the vertical mixing of heat and water vapor, which has an impact on downwind meteorological conditions, including rainfall.n